On the complexity of hypothesis space and the sample complexity for machine learning
The problem of learning a concept from examples in the model introduced by Valiant (1984) is discussed. According to the traditional ways of thinking, it is assumed that the learnability is independent of the occurrence probability of instance. By utilizing this probability, we propose the metric as...
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 | 137 vol.1 |
|---|---|
| container_issue | |
| container_start_page | 132 |
| container_title | |
| container_volume | 1 |
| creator | Nakazawa, M. Kohnosu, T. Matsushima, T. Hirasawa, S. |
| description | The problem of learning a concept from examples in the model introduced by Valiant (1984) is discussed. According to the traditional ways of thinking, it is assumed that the learnability is independent of the occurrence probability of instance. By utilizing this probability, we propose the metric as a new measure to determine the complexity of hypothesis space. The metric measures the hardness of discrimination between hypotheses. Furthermore, we obtain the average metric dependent on prior information. This metric is the measure of complexity for hypothesis space in the average. Similarly in the worst case, we obtain the minimum metric. We make clear the relationship between these measures and the Vapnik-Chervonenkis (VC) dimension. Finally, we show the upper bound on sample complexity utilizing the metric. This results can be applied in the discussion on the learnability of the class with an infinite VC dimension.< > |
| doi_str_mv | 10.1109/ICSMC.1994.399824 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_399824</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>399824</ieee_id><sourcerecordid>399824</sourcerecordid><originalsourceid>FETCH-LOGICAL-i104t-967495fc7796c8659fe7650165585187b986dcb6426861bcc03fa8de7e47263f3</originalsourceid><addsrcrecordid>eNpNj8tKxDAYhQMiKGMfQFd5gdakuf5LKV4GRmbhuB7S9I-NTC80Xdi3tzouPBw4cPg4cAi55azgnMH9tnp7rQoOIAsBYEt5QTIwlq0WJS_BXpEspU-2Siolubkmh31P5xapH7rxhF9xXugQaLuMw9qmmGganUfq-uYXS-4H-0-HYaKd823skZ7QTX3sP27IZXCnhNlfbsj70-Ohesl3--dt9bDLI2dyzkEbCSp4Y0B7qxUENFoxrpWyiltTg9WNr7UstdW89p6J4GyDBqUptQhiQ-7OuxERj-MUOzctx_N18Q0_3U8N</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>On the complexity of hypothesis space and the sample complexity for machine learning</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Nakazawa, M. ; Kohnosu, T. ; Matsushima, T. ; Hirasawa, S.</creator><creatorcontrib>Nakazawa, M. ; Kohnosu, T. ; Matsushima, T. ; Hirasawa, S.</creatorcontrib><description>The problem of learning a concept from examples in the model introduced by Valiant (1984) is discussed. According to the traditional ways of thinking, it is assumed that the learnability is independent of the occurrence probability of instance. By utilizing this probability, we propose the metric as a new measure to determine the complexity of hypothesis space. The metric measures the hardness of discrimination between hypotheses. Furthermore, we obtain the average metric dependent on prior information. This metric is the measure of complexity for hypothesis space in the average. Similarly in the worst case, we obtain the minimum metric. We make clear the relationship between these measures and the Vapnik-Chervonenkis (VC) dimension. Finally, we show the upper bound on sample complexity utilizing the metric. This results can be applied in the discussion on the learnability of the class with an infinite VC dimension.< ></description><identifier>ISBN: 9780780321298</identifier><identifier>ISBN: 0780321294</identifier><identifier>DOI: 10.1109/ICSMC.1994.399824</identifier><language>eng</language><publisher>IEEE</publisher><subject>Engineering management ; Extraterrestrial measurements ; Industrial engineering ; Machine learning ; Telecommunications ; Upper bound ; Virtual colonoscopy</subject><ispartof>Proceedings of IEEE International Conference on Systems, Man and Cybernetics, 1994, Vol.1, p.132-137 vol.1</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/399824$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,4036,4037,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/399824$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Nakazawa, M.</creatorcontrib><creatorcontrib>Kohnosu, T.</creatorcontrib><creatorcontrib>Matsushima, T.</creatorcontrib><creatorcontrib>Hirasawa, S.</creatorcontrib><title>On the complexity of hypothesis space and the sample complexity for machine learning</title><title>Proceedings of IEEE International Conference on Systems, Man and Cybernetics</title><addtitle>ICSMC</addtitle><description>The problem of learning a concept from examples in the model introduced by Valiant (1984) is discussed. According to the traditional ways of thinking, it is assumed that the learnability is independent of the occurrence probability of instance. By utilizing this probability, we propose the metric as a new measure to determine the complexity of hypothesis space. The metric measures the hardness of discrimination between hypotheses. Furthermore, we obtain the average metric dependent on prior information. This metric is the measure of complexity for hypothesis space in the average. Similarly in the worst case, we obtain the minimum metric. We make clear the relationship between these measures and the Vapnik-Chervonenkis (VC) dimension. Finally, we show the upper bound on sample complexity utilizing the metric. This results can be applied in the discussion on the learnability of the class with an infinite VC dimension.< ></description><subject>Engineering management</subject><subject>Extraterrestrial measurements</subject><subject>Industrial engineering</subject><subject>Machine learning</subject><subject>Telecommunications</subject><subject>Upper bound</subject><subject>Virtual colonoscopy</subject><isbn>9780780321298</isbn><isbn>0780321294</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>1994</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpNj8tKxDAYhQMiKGMfQFd5gdakuf5LKV4GRmbhuB7S9I-NTC80Xdi3tzouPBw4cPg4cAi55azgnMH9tnp7rQoOIAsBYEt5QTIwlq0WJS_BXpEspU-2Siolubkmh31P5xapH7rxhF9xXugQaLuMw9qmmGganUfq-uYXS-4H-0-HYaKd823skZ7QTX3sP27IZXCnhNlfbsj70-Ohesl3--dt9bDLI2dyzkEbCSp4Y0B7qxUENFoxrpWyiltTg9WNr7UstdW89p6J4GyDBqUptQhiQ-7OuxERj-MUOzctx_N18Q0_3U8N</recordid><startdate>1994</startdate><enddate>1994</enddate><creator>Nakazawa, M.</creator><creator>Kohnosu, T.</creator><creator>Matsushima, T.</creator><creator>Hirasawa, S.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>1994</creationdate><title>On the complexity of hypothesis space and the sample complexity for machine learning</title><author>Nakazawa, M. ; Kohnosu, T. ; Matsushima, T. ; Hirasawa, S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i104t-967495fc7796c8659fe7650165585187b986dcb6426861bcc03fa8de7e47263f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>1994</creationdate><topic>Engineering management</topic><topic>Extraterrestrial measurements</topic><topic>Industrial engineering</topic><topic>Machine learning</topic><topic>Telecommunications</topic><topic>Upper bound</topic><topic>Virtual colonoscopy</topic><toplevel>online_resources</toplevel><creatorcontrib>Nakazawa, M.</creatorcontrib><creatorcontrib>Kohnosu, T.</creatorcontrib><creatorcontrib>Matsushima, T.</creatorcontrib><creatorcontrib>Hirasawa, S.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Nakazawa, M.</au><au>Kohnosu, T.</au><au>Matsushima, T.</au><au>Hirasawa, S.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>On the complexity of hypothesis space and the sample complexity for machine learning</atitle><btitle>Proceedings of IEEE International Conference on Systems, Man and Cybernetics</btitle><stitle>ICSMC</stitle><date>1994</date><risdate>1994</risdate><volume>1</volume><spage>132</spage><epage>137 vol.1</epage><pages>132-137 vol.1</pages><isbn>9780780321298</isbn><isbn>0780321294</isbn><abstract>The problem of learning a concept from examples in the model introduced by Valiant (1984) is discussed. According to the traditional ways of thinking, it is assumed that the learnability is independent of the occurrence probability of instance. By utilizing this probability, we propose the metric as a new measure to determine the complexity of hypothesis space. The metric measures the hardness of discrimination between hypotheses. Furthermore, we obtain the average metric dependent on prior information. This metric is the measure of complexity for hypothesis space in the average. Similarly in the worst case, we obtain the minimum metric. We make clear the relationship between these measures and the Vapnik-Chervonenkis (VC) dimension. Finally, we show the upper bound on sample complexity utilizing the metric. This results can be applied in the discussion on the learnability of the class with an infinite VC dimension.< ></abstract><pub>IEEE</pub><doi>10.1109/ICSMC.1994.399824</doi></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 9780780321298 |
| ispartof | Proceedings of IEEE International Conference on Systems, Man and Cybernetics, 1994, Vol.1, p.132-137 vol.1 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_399824 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Engineering management Extraterrestrial measurements Industrial engineering Machine learning Telecommunications Upper bound Virtual colonoscopy |
| title | On the complexity of hypothesis space and the sample complexity for machine learning |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T15%3A09%3A23IST&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=On%20the%20complexity%20of%20hypothesis%20space%20and%20the%20sample%20complexity%20for%20machine%20learning&rft.btitle=Proceedings%20of%20IEEE%20International%20Conference%20on%20Systems,%20Man%20and%20Cybernetics&rft.au=Nakazawa,%20M.&rft.date=1994&rft.volume=1&rft.spage=132&rft.epage=137%20vol.1&rft.pages=132-137%20vol.1&rft.isbn=9780780321298&rft.isbn_list=0780321294&rft_id=info:doi/10.1109/ICSMC.1994.399824&rft_dat=%3Cieee_6IE%3E399824%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=399824&rfr_iscdi=true |