Generalizing over Several Learning Settings
Identifieur interne : 000B78 ( Main/Exploration ); précédent : 000B77; suivant : 000B79Generalizing over Several Learning Settings
Auteurs : Anna Kasprzik [Allemagne]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2010.
Abstract
Abstract: We recapitulate inference from membership and equivalence queries, positive and negative samples. Regular languages cannot be learned from one of those information sources only [1,2,3]. Combinations of two sources allowing regular (polynomial) inference are MQs and EQs [4], MQs and positive data [5,6], positive and negative data [7,8]. We sketch a meta-algorithm fully presented in [9] that generalizes over as many combinations of those sources as possible. This includes a survey of pairings for which there are no well-studied algorithms.
Url:
DOI: 10.1007/978-3-642-15488-1_28
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000C10
- to stream Istex, to step Curation: 000B39
- to stream Istex, to step Checkpoint: 000257
- to stream Main, to step Merge: 000C32
- to stream Main, to step Curation: 000B78
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct:series"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Generalizing over Several Learning Settings</title><author><name sortKey="Kasprzik, Anna" sort="Kasprzik, Anna" uniqKey="Kasprzik A" first="Anna" last="Kasprzik">Anna Kasprzik</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:76C981C39E161243487E92ECE2960115A0240FA2</idno><date when="2010" year="2010">2010</date><idno type="doi">10.1007/978-3-642-15488-1_28</idno><idno type="url">https://api.istex.fr/document/76C981C39E161243487E92ECE2960115A0240FA2/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000C10</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000C10</idno><idno type="wicri:Area/Istex/Curation">000B39</idno><idno type="wicri:Area/Istex/Checkpoint">000257</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000257</idno><idno type="wicri:doubleKey">0302-9743:2010:Kasprzik A:generalizing:over:several</idno><idno type="wicri:Area/Main/Merge">000C32</idno><idno type="wicri:Area/Main/Curation">000B78</idno><idno type="wicri:Area/Main/Exploration">000B78</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Generalizing over Several Learning Settings</title><author><name sortKey="Kasprzik, Anna" sort="Kasprzik, Anna" uniqKey="Kasprzik A" first="Anna" last="Kasprzik">Anna Kasprzik</name><affiliation wicri:level="4"><country>Allemagne</country><placeName><settlement type="city">Trèves (Allemagne)</settlement><region type="land" nuts="1">Rhénanie-Palatinat</region></placeName><orgName type="university">Université de Trèves</orgName></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Allemagne</country></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>2010</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">76C981C39E161243487E92ECE2960115A0240FA2</idno><idno type="DOI">10.1007/978-3-642-15488-1_28</idno><idno type="ChapterID">28</idno><idno type="ChapterID">Chap28</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0302-9743</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: We recapitulate inference from membership and equivalence queries, positive and negative samples. Regular languages cannot be learned from one of those information sources only [1,2,3]. Combinations of two sources allowing regular (polynomial) inference are MQs and EQs [4], MQs and positive data [5,6], positive and negative data [7,8]. We sketch a meta-algorithm fully presented in [9] that generalizes over as many combinations of those sources as possible. This includes a survey of pairings for which there are no well-studied algorithms.</div></front></TEI><affiliations><list><country><li>Allemagne</li></country><region><li>Rhénanie-Palatinat</li></region><settlement><li>Trèves (Allemagne)</li></settlement><orgName><li>Université de Trèves</li></orgName></list><tree><country name="Allemagne"><region name="Rhénanie-Palatinat"><name sortKey="Kasprzik, Anna" sort="Kasprzik, Anna" uniqKey="Kasprzik A" first="Anna" last="Kasprzik">Anna Kasprzik</name></region><name sortKey="Kasprzik, Anna" sort="Kasprzik, Anna" uniqKey="Kasprzik A" first="Anna" last="Kasprzik">Anna Kasprzik</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Rhénanie/explor/UnivTrevesV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000B78 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000B78 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Rhénanie
|area= UnivTrevesV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:76C981C39E161243487E92ECE2960115A0240FA2
|texte= Generalizing over Several Learning Settings
}}
| This area was generated with Dilib version V0.6.31. |  |