An Analysis of the Anti-Learning Phenomenon for the Class Symmetric Polyhedron

Kowalczyk, A; Chapelle, O

doi:10.1007/11564089_8

Lokale TagsFreigabegeschichteDetailsÜbersicht

An Analysis of the Anti-Learning Phenomenon for the Class Symmetric Polyhedron

Kowalczyk, A., & Chapelle, O. (2005). An Analysis of the Anti-Learning Phenomenon for the Class Symmetric Polyhedron. In S. Jain, H. Simon, & E. Tomita (Eds.), Algorithmic Learning Theory: 16th International Conference, ALT 2005, Singapore, October 8-11, 2005 (pp. 78-92). Berlin, Germany: Springer.

Item is Freigegeben

einblenden: alle

Basisdaten

ausblenden:

Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-D3FD-9 Versions-Permalink: https://hdl.handle.net/21.11116/0000-0005-0D9E-C

Genre: Konferenzbeitrag

Dateien

einblenden: Dateien

Externe Referenzen

ausblenden:

externe Referenz:
https://link.springer.com/content/pdf/10.1007%2F11564089_8.pdf (Verlagsversion) Open Access Status unbekannt

Beschreibung:
-

OA-Status:

Urheber

ausblenden:

Urheber:
Kowalczyk, A, Autor
Chapelle, O^{1, 2}, Autor

Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794

Inhalt

ausblenden:

Schlagwörter: -

Zusammenfassung: This paper deals with an unusual phenomenon where most machine learning algorithms yield good performance on the training set but systematically worse than random performance on the test set. This has been observed so far for some natural data sets and demonstrated for some synthetic data sets when the classification rule is learned from a small set of training samples drawn from some high dimensional space. The initial analysis presented in this paper shows that anti-learning is a property of data sets and is quite distinct from overfitting of a training data. Moreover, the analysis leads to a specification of some machine learning procedures which can overcome anti-learning and generate ma- chines able to classify training and test data consistently.

Details

ausblenden:

Sprache(n):

Datum: Erschienen: 2005-10

Publikationsstatus: Erschienen

Seiten: -

Ort, Verlag, Ausgabe: -

Inhaltsverzeichnis: -

Art der Begutachtung: -

Identifikatoren: BibTex Citekey: 3604
DOI: 10.1007/11564089_8

Art des Abschluß: -

Veranstaltung

ausblenden:

Titel: 16th International Conference on Algorithmic Learning Theory (ALT 2005)

Veranstaltungsort: Singapore

Start-/Enddatum: 2005-10-08 - 2005-10-11

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

ausblenden:

Titel: Algorithmic Learning Theory: 16th International Conference, ALT 2005, Singapore, October 8-11, 2005

Genre der Quelle: Konferenzband

Urheber:
Jain, S, Herausgeber
Simon, HU, Herausgeber
Tomita, E, Herausgeber

Affiliations:
-

Ort, Verlag, Ausgabe: Berlin, Germany : Springer

Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 78 - 92 Identifikator: ISBN: 978-3-540-29242-5

Quelle 2

ausblenden:

Titel: Lecture Notes in Computer Science

Genre der Quelle: Reihe

Urheber:

Affiliations:

Ort, Verlag, Ausgabe: -

Seiten: - Band / Heft: 3734 Artikelnummer: - Start- / Endseite: - Identifikator: -