Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

 
 
DownloadE-Mail
  Solutions to Open Questions for Non-U-Shaped Learning with Memory Limitations

Case, J., & Kötzing, T. (2010). Solutions to Open Questions for Non-U-Shaped Learning with Memory Limitations. In M. Hutter, F. Stephan, V. Vovk, & T. Zeugmann (Eds.), Algorithmic Learning Theory (pp. 285-299). Berlin: Springer. doi:10.1007/978-3-642-16108-7_24.

Item is

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Case, John1, Autor
Kötzing, Timo2, Autor           
Affiliations:
1External Organizations, ou_persistent22              
2Algorithms and Complexity, MPI for Informatics, Max Planck Society, ou_24019              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: A U-shape occurs when a learner first learns, then unlearns, and, finally, relearns, some target concept. Within the framework of Inductive Inference, previous results have shown, for example, that U-shapes are unnecessary for explanatory learning, but are necessary for behaviorally correct learning. This paper solves the following two problems regarding non-U-shaped learning posed in the prior literature. First, it is shown that there are classes learnable with three memory states that are not learnable non-U-shapedly with any finite number of memory states. This result is surprising, as for learning with one or two memory states, U-shapes are known to be unnecessary. Secondly, it is shown that there is a class learnable memorylessly with a single feedback query such that this class is not learnable non-U-shapedly memorylessly with any finite number of feedback queries. This result is complemented by the result that any class of \emph{infinite} languages learnable memorylessly with finitely many feedback queries is so learnable without U-shapes -- in fact, all classes of infinite languages learnable with \emph{complete} memory are learnable memorylessly with finitely many feedback queries and without U-shapes. On the other hand, we show that there is a class of infinite languages learnable memorylessly with a single feedback query, which is \emph{not} learnable with\emph{out} U-shapes by any particular bounded number of feedback queries.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 20102010
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: eDoc: 536694
DOI: 10.1007/978-3-642-16108-7_24
Anderer: Local-ID: C1256428004B93B8-62C151E58D79F70FC12577F80053535A-Koetzing2010NUMemLimited
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: 21st International Conference on Algorithmic Learning Theory
Veranstaltungsort: Canberra, Australia
Start-/Enddatum: 2010-12-13 - 2010-12-13

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Algorithmic Learning Theory
Genre der Quelle: Konferenzband
 Urheber:
Hutter, Marcus1, Herausgeber
Stephan, Frank1, Herausgeber
Vovk, Vladimir1, Herausgeber
Zeugmann, Thomas1, Herausgeber
Affiliations:
1 External Organizations, ou_persistent22            
Ort, Verlag, Ausgabe: Berlin : Springer
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 285 - 299 Identifikator: ISBN: 978-3-642-16107-0

Quelle 2

einblenden:
ausblenden:
Titel: Lecture Notes in Artificial Intelligence
  Kurztitel : LNAI
Genre der Quelle: Reihe
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: -
Seiten: - Band / Heft: 6331 Artikelnummer: - Start- / Endseite: - Identifikator: -