Exact Learning Composed Classes with a Small Number of Mistakes
The Composition Lemma is one of the strongest tools for learning complex classes. It shows that if a class is learnable then composing the class with a class of polynomial number of concepts gives a learnable class. In this paper we extend the Composition Lemma as follows: we show that composing an...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 213 |
|---|---|
| container_issue | |
| container_start_page | 199 |
| container_title | |
| container_volume | |
| creator | Bshouty, Nader H. Mazzawi, Hanna |
| description | The Composition Lemma is one of the strongest tools for learning complex classes. It shows that if a class is learnable then composing the class with a class of polynomial number of concepts gives a learnable class. In this paper we extend the Composition Lemma as follows: we show that composing an attribute efficient learnable class with a learnable class with polynomial shatter coefficient gives a learnable class.
This result extends many results in the literature and gives polynomial learning algorithms for new classes. |
| doi_str_mv | 10.1007/11776420_17 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>pascalfrancis_sprin</sourceid><recordid>TN_cdi_pascalfrancis_primary_19150822</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>19150822</sourcerecordid><originalsourceid>FETCH-LOGICAL-p219t-b8a0dab2d5e2bb7db365eecc7b5273eb2816e90b6f4f73e51cb284241dff935d3</originalsourceid><addsrcrecordid>eNpNkLlOxDAURc0mkRmm4gfcUFAE_J7tOK4QioZFClAAdWQn9hAmm-Ig4O-JNCBRXd1FtziEnAK7AMbUJYBSiUBWgNojK61SLgXjEnWi90kECUDMudAHZPFXCHlIIsYZxloJfkwWIbwzxlBpjMjV-suUE82dGbu629Csb4c-uIpmjQnBBfpZT2_U0OfWNA19_GitG2nv6UMdJrN14YQcedMEt_rVJXm9Wb9kd3H-dHufXefxgKCn2KaGVcZiJR1aqyrLE-lcWSorUXFnMYXEaWYTL_zsJZRzJFBA5b3msuJLcrb7HUwoTeNH05V1KIaxbs34XYAGyVLEeXe-24W56jZuLGzfb0MBM7AZX_EPH_8BLUxcVw</addsrcrecordid><sourcetype>Index Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Exact Learning Composed Classes with a Small Number of Mistakes</title><source>Springer Books</source><creator>Bshouty, Nader H. ; Mazzawi, Hanna</creator><contributor>Lugosi, Gábor ; Simon, Hans Ulrich</contributor><creatorcontrib>Bshouty, Nader H. ; Mazzawi, Hanna ; Lugosi, Gábor ; Simon, Hans Ulrich</creatorcontrib><description>The Composition Lemma is one of the strongest tools for learning complex classes. It shows that if a class is learnable then composing the class with a class of polynomial number of concepts gives a learnable class. In this paper we extend the Composition Lemma as follows: we show that composing an attribute efficient learnable class with a learnable class with polynomial shatter coefficient gives a learnable class.
This result extends many results in the literature and gives polynomial learning algorithms for new classes.</description><identifier>ISSN: 0302-9743</identifier><identifier>ISBN: 3540352945</identifier><identifier>ISBN: 9783540352945</identifier><identifier>EISSN: 1611-3349</identifier><identifier>EISBN: 9783540352969</identifier><identifier>EISBN: 3540352961</identifier><identifier>DOI: 10.1007/11776420_17</identifier><language>eng</language><publisher>Berlin, Heidelberg: Springer Berlin Heidelberg</publisher><subject>Applied sciences ; Artificial intelligence ; Computer science; control theory; systems ; Exact sciences and technology</subject><ispartof>Learning Theory, 2006, p.199-213</ispartof><rights>Springer-Verlag Berlin Heidelberg 2006</rights><rights>2007 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/11776420_17$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/11776420_17$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>310,311,780,781,785,790,791,794,4051,4052,27930,38260,41447,42516</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=19150822$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><contributor>Lugosi, Gábor</contributor><contributor>Simon, Hans Ulrich</contributor><creatorcontrib>Bshouty, Nader H.</creatorcontrib><creatorcontrib>Mazzawi, Hanna</creatorcontrib><title>Exact Learning Composed Classes with a Small Number of Mistakes</title><title>Learning Theory</title><description>The Composition Lemma is one of the strongest tools for learning complex classes. It shows that if a class is learnable then composing the class with a class of polynomial number of concepts gives a learnable class. In this paper we extend the Composition Lemma as follows: we show that composing an attribute efficient learnable class with a learnable class with polynomial shatter coefficient gives a learnable class.
This result extends many results in the literature and gives polynomial learning algorithms for new classes.</description><subject>Applied sciences</subject><subject>Artificial intelligence</subject><subject>Computer science; control theory; systems</subject><subject>Exact sciences and technology</subject><issn>0302-9743</issn><issn>1611-3349</issn><isbn>3540352945</isbn><isbn>9783540352945</isbn><isbn>9783540352969</isbn><isbn>3540352961</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2006</creationdate><recordtype>conference_proceeding</recordtype><recordid>eNpNkLlOxDAURc0mkRmm4gfcUFAE_J7tOK4QioZFClAAdWQn9hAmm-Ig4O-JNCBRXd1FtziEnAK7AMbUJYBSiUBWgNojK61SLgXjEnWi90kECUDMudAHZPFXCHlIIsYZxloJfkwWIbwzxlBpjMjV-suUE82dGbu629Csb4c-uIpmjQnBBfpZT2_U0OfWNA19_GitG2nv6UMdJrN14YQcedMEt_rVJXm9Wb9kd3H-dHufXefxgKCn2KaGVcZiJR1aqyrLE-lcWSorUXFnMYXEaWYTL_zsJZRzJFBA5b3msuJLcrb7HUwoTeNH05V1KIaxbs34XYAGyVLEeXe-24W56jZuLGzfb0MBM7AZX_EPH_8BLUxcVw</recordid><startdate>2006</startdate><enddate>2006</enddate><creator>Bshouty, Nader H.</creator><creator>Mazzawi, Hanna</creator><general>Springer Berlin Heidelberg</general><general>Springer</general><scope>IQODW</scope></search><sort><creationdate>2006</creationdate><title>Exact Learning Composed Classes with a Small Number of Mistakes</title><author>Bshouty, Nader H. ; Mazzawi, Hanna</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-p219t-b8a0dab2d5e2bb7db365eecc7b5273eb2816e90b6f4f73e51cb284241dff935d3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2006</creationdate><topic>Applied sciences</topic><topic>Artificial intelligence</topic><topic>Computer science; control theory; systems</topic><topic>Exact sciences and technology</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Bshouty, Nader H.</creatorcontrib><creatorcontrib>Mazzawi, Hanna</creatorcontrib><collection>Pascal-Francis</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Bshouty, Nader H.</au><au>Mazzawi, Hanna</au><au>Lugosi, Gábor</au><au>Simon, Hans Ulrich</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Exact Learning Composed Classes with a Small Number of Mistakes</atitle><btitle>Learning Theory</btitle><date>2006</date><risdate>2006</risdate><spage>199</spage><epage>213</epage><pages>199-213</pages><issn>0302-9743</issn><eissn>1611-3349</eissn><isbn>3540352945</isbn><isbn>9783540352945</isbn><eisbn>9783540352969</eisbn><eisbn>3540352961</eisbn><abstract>The Composition Lemma is one of the strongest tools for learning complex classes. It shows that if a class is learnable then composing the class with a class of polynomial number of concepts gives a learnable class. In this paper we extend the Composition Lemma as follows: we show that composing an attribute efficient learnable class with a learnable class with polynomial shatter coefficient gives a learnable class.
This result extends many results in the literature and gives polynomial learning algorithms for new classes.</abstract><cop>Berlin, Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/11776420_17</doi><tpages>15</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0302-9743 |
| ispartof | Learning Theory, 2006, p.199-213 |
| issn | 0302-9743 1611-3349 |
| language | eng |
| recordid | cdi_pascalfrancis_primary_19150822 |
| source | Springer Books |
| subjects | Applied sciences Artificial intelligence Computer science control theory systems Exact sciences and technology |
| title | Exact Learning Composed Classes with a Small Number of Mistakes |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-14T08%3A57%3A34IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-pascalfrancis_sprin&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Exact%20Learning%20Composed%20Classes%20with%20a%20Small%20Number%20of%20Mistakes&rft.btitle=Learning%20Theory&rft.au=Bshouty,%20Nader%20H.&rft.date=2006&rft.spage=199&rft.epage=213&rft.pages=199-213&rft.issn=0302-9743&rft.eissn=1611-3349&rft.isbn=3540352945&rft.isbn_list=9783540352945&rft_id=info:doi/10.1007/11776420_17&rft_dat=%3Cpascalfrancis_sprin%3E19150822%3C/pascalfrancis_sprin%3E%3Curl%3E%3C/url%3E&rft.eisbn=9783540352969&rft.eisbn_list=3540352961&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |