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

Kowalczyk, A; Chapelle, O

doi:10.1007/11564089_8

Datensatz

DATENSATZ AKTIONENEXPORT

Zur Ablage hinzufügen

Lokale TagsFreigabegeschichteDetailsÜbersicht

Freigegeben

Konferenzbeitrag

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

MPG-Autoren

/persons/resource/persons83855

Chapelle, O
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

Externe Ressourcen

https://link.springer.com/content/pdf/10.1007%2F11564089_8.pdf
(Verlagsversion)

Volltexte (beschränkter Zugriff)

Für Ihren IP-Bereich sind aktuell keine Volltexte freigegeben.

Volltexte (frei zugänglich)

Es sind keine frei zugänglichen Volltexte in PuRe verfügbar

Ergänzendes Material (frei zugänglich)

Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar

Zitation

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.

Zitierlink: https://hdl.handle.net/11858/00-001M-0000-0013-D3FD-9

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.