Recursion theoretic characterizations of language learning:
Abstract: "An attempt is made to build 'bridges' between machine language learning and recursive function theory. Formal language learning classes are characterized in terms of recursion theoretic notions like standardizing operations and recursively enumerable classes. Connections be...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
Rochester, NY
1989
|
| Schriftenreihe: | University of Rochester <Rochester, NY> / Department of Computer Science: Technical report
281 |
| Schlagworte: | |
| Zusammenfassung: | Abstract: "An attempt is made to build 'bridges' between machine language learning and recursive function theory. Formal language learning classes are characterized in terms of recursion theoretic notions like standardizing operations and recursively enumerable classes. Connections between Gold's seminal notion of identification, referred to as TxtEx-identification, and standardizing operations are investigated. It is shown that the class of languages that can be TxtEx-identified is properly contained in the class of languages that are limit-effectively standardizable. A restricted form of standardizability, which has the same power as TxtEx-identification, is presented The notion of TxtEx-identification is relaxed (by providing additional information about the language being learned), so that the classes of languages that can be identified by this new criterion are exactly the same as the classes of languages that are limit-effectively standardizable. A connection between the above criteria and r.e. class of languages is also investigated. It is shown that for the class of languages identified by the above criteria, there exists a computable numbering that has exactly one index for infinite languages in the class and a finite number of indices for the finite languages in the class. Motivation for these characterizations are derived from the work of Freivald's, Kinber, and Wiehagen on the inference of programs for recursive functions from their graphs However, new notions have to be invented to characterize language learning, and proofs are considerably more difficult. |
| Beschreibung: | 32 S. |
Internformat
MARC
| LEADER | 00000nam a2200000 cb4500 | ||
|---|---|---|---|
| 001 | BV008948973 | ||
| 003 | DE-604 | ||
| 005 | 20090709 | ||
| 007 | t | ||
| 008 | 940206s1989 |||| 00||| eng d | ||
| 035 | |a (OCoLC)21913912 | ||
| 035 | |a (DE-599)BVBBV008948973 | ||
| 040 | |a DE-604 |b ger |e rakddb | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-29T | ||
| 100 | 1 | |a Jain, Sanjay |e Verfasser |0 (DE-588)130399949 |4 aut | |
| 245 | 1 | 0 | |a Recursion theoretic characterizations of language learning |c Sanjay Jain ; Arun Sharma |
| 264 | 1 | |a Rochester, NY |c 1989 | |
| 300 | |a 32 S. | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 490 | 1 | |a University of Rochester <Rochester, NY> / Department of Computer Science: Technical report |v 281 | |
| 520 | 3 | |a Abstract: "An attempt is made to build 'bridges' between machine language learning and recursive function theory. Formal language learning classes are characterized in terms of recursion theoretic notions like standardizing operations and recursively enumerable classes. Connections between Gold's seminal notion of identification, referred to as TxtEx-identification, and standardizing operations are investigated. It is shown that the class of languages that can be TxtEx-identified is properly contained in the class of languages that are limit-effectively standardizable. A restricted form of standardizability, which has the same power as TxtEx-identification, is presented | |
| 520 | 3 | |a The notion of TxtEx-identification is relaxed (by providing additional information about the language being learned), so that the classes of languages that can be identified by this new criterion are exactly the same as the classes of languages that are limit-effectively standardizable. A connection between the above criteria and r.e. class of languages is also investigated. It is shown that for the class of languages identified by the above criteria, there exists a computable numbering that has exactly one index for infinite languages in the class and a finite number of indices for the finite languages in the class. Motivation for these characterizations are derived from the work of Freivald's, Kinber, and Wiehagen on the inference of programs for recursive functions from their graphs | |
| 520 | 3 | |a However, new notions have to be invented to characterize language learning, and proofs are considerably more difficult. | |
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a Recursion theory | |
| 700 | 1 | |a Sharma, Arun |e Verfasser |4 aut | |
| 810 | 2 | |a Department of Computer Science: Technical report |t University of Rochester <Rochester, NY> |v 281 |w (DE-604)BV008902697 |9 281 | |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-005904693 | ||
Datensatz im Suchindex
| _version_ | 1804123281984323584 |
|---|---|
| any_adam_object | |
| author | Jain, Sanjay Sharma, Arun |
| author_GND | (DE-588)130399949 |
| author_facet | Jain, Sanjay Sharma, Arun |
| author_role | aut aut |
| author_sort | Jain, Sanjay |
| author_variant | s j sj a s as |
| building | Verbundindex |
| bvnumber | BV008948973 |
| ctrlnum | (OCoLC)21913912 (DE-599)BVBBV008948973 |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>02687nam a2200337 cb4500</leader><controlfield tag="001">BV008948973</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20090709 </controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">940206s1989 |||| 00||| eng d</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)21913912</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV008948973</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rakddb</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-29T</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Jain, Sanjay</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)130399949</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Recursion theoretic characterizations of language learning</subfield><subfield code="c">Sanjay Jain ; Arun Sharma</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Rochester, NY</subfield><subfield code="c">1989</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">32 S.</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="490" ind1="1" ind2=" "><subfield code="a">University of Rochester <Rochester, NY> / Department of Computer Science: Technical report</subfield><subfield code="v">281</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Abstract: "An attempt is made to build 'bridges' between machine language learning and recursive function theory. Formal language learning classes are characterized in terms of recursion theoretic notions like standardizing operations and recursively enumerable classes. Connections between Gold's seminal notion of identification, referred to as TxtEx-identification, and standardizing operations are investigated. It is shown that the class of languages that can be TxtEx-identified is properly contained in the class of languages that are limit-effectively standardizable. A restricted form of standardizability, which has the same power as TxtEx-identification, is presented</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">The notion of TxtEx-identification is relaxed (by providing additional information about the language being learned), so that the classes of languages that can be identified by this new criterion are exactly the same as the classes of languages that are limit-effectively standardizable. A connection between the above criteria and r.e. class of languages is also investigated. It is shown that for the class of languages identified by the above criteria, there exists a computable numbering that has exactly one index for infinite languages in the class and a finite number of indices for the finite languages in the class. Motivation for these characterizations are derived from the work of Freivald's, Kinber, and Wiehagen on the inference of programs for recursive functions from their graphs</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">However, new notions have to be invented to characterize language learning, and proofs are considerably more difficult.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Recursion theory</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Sharma, Arun</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="810" ind1="2" ind2=" "><subfield code="a">Department of Computer Science: Technical report</subfield><subfield code="t">University of Rochester <Rochester, NY></subfield><subfield code="v">281</subfield><subfield code="w">(DE-604)BV008902697</subfield><subfield code="9">281</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-005904693</subfield></datafield></record></collection> |
| id | DE-604.BV008948973 |
| illustrated | Not Illustrated |
| indexdate | 2024-07-09T17:27:17Z |
| institution | BVB |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-005904693 |
| oclc_num | 21913912 |
| open_access_boolean | |
| owner | DE-29T |
| owner_facet | DE-29T |
| physical | 32 S. |
| publishDate | 1989 |
| publishDateSearch | 1989 |
| publishDateSort | 1989 |
| record_format | marc |
| series2 | University of Rochester <Rochester, NY> / Department of Computer Science: Technical report |
| spelling | Jain, Sanjay Verfasser (DE-588)130399949 aut Recursion theoretic characterizations of language learning Sanjay Jain ; Arun Sharma Rochester, NY 1989 32 S. txt rdacontent n rdamedia nc rdacarrier University of Rochester <Rochester, NY> / Department of Computer Science: Technical report 281 Abstract: "An attempt is made to build 'bridges' between machine language learning and recursive function theory. Formal language learning classes are characterized in terms of recursion theoretic notions like standardizing operations and recursively enumerable classes. Connections between Gold's seminal notion of identification, referred to as TxtEx-identification, and standardizing operations are investigated. It is shown that the class of languages that can be TxtEx-identified is properly contained in the class of languages that are limit-effectively standardizable. A restricted form of standardizability, which has the same power as TxtEx-identification, is presented The notion of TxtEx-identification is relaxed (by providing additional information about the language being learned), so that the classes of languages that can be identified by this new criterion are exactly the same as the classes of languages that are limit-effectively standardizable. A connection between the above criteria and r.e. class of languages is also investigated. It is shown that for the class of languages identified by the above criteria, there exists a computable numbering that has exactly one index for infinite languages in the class and a finite number of indices for the finite languages in the class. Motivation for these characterizations are derived from the work of Freivald's, Kinber, and Wiehagen on the inference of programs for recursive functions from their graphs However, new notions have to be invented to characterize language learning, and proofs are considerably more difficult. Machine learning Recursion theory Sharma, Arun Verfasser aut Department of Computer Science: Technical report University of Rochester <Rochester, NY> 281 (DE-604)BV008902697 281 |
| spellingShingle | Jain, Sanjay Sharma, Arun Recursion theoretic characterizations of language learning Machine learning Recursion theory |
| title | Recursion theoretic characterizations of language learning |
| title_auth | Recursion theoretic characterizations of language learning |
| title_exact_search | Recursion theoretic characterizations of language learning |
| title_full | Recursion theoretic characterizations of language learning Sanjay Jain ; Arun Sharma |
| title_fullStr | Recursion theoretic characterizations of language learning Sanjay Jain ; Arun Sharma |
| title_full_unstemmed | Recursion theoretic characterizations of language learning Sanjay Jain ; Arun Sharma |
| title_short | Recursion theoretic characterizations of language learning |
| title_sort | recursion theoretic characterizations of language learning |
| topic | Machine learning Recursion theory |
| topic_facet | Machine learning Recursion theory |
| volume_link | (DE-604)BV008902697 |
| work_keys_str_mv | AT jainsanjay recursiontheoreticcharacterizationsoflanguagelearning AT sharmaarun recursiontheoreticcharacterizationsoflanguagelearning |