Journalartikel

Jahr der Veröffentlichung: 2005

Seiten: 109-120

Zeitschrift: Neural Processing Letters

Bandnummer: 21

Heftnummer: 2

ISSN: 1370-4621

eISSN: 1573-773X

DOI Link: https://doi.org/10.1007/s11063-004-1547-1

Verlag: Springer

Abstract: 
We derive a generalization bound for prototype-based classifiers with adaptive metric. The bound depends on the margin of the classifier and is independent of the dimensionality of the data. It holds for classifiers based on the Euclidean metric extended by adaptive relevance terms. In particular, the result holds for relevance learning vector quantization (RLVQ) [4] and generalized relevance learning vector quantization (GRLVQ) [19].

Harvard-Zitierstil: Hammer, B., Strickert, M. and Villmann, T. (2005) On the generalization ability of GRLVQ networks, Neural Processing Letters, 21(2), pp. 109-120. https://doi.org/10.1007/s11063-004-1547-1

APA-Zitierstil: Hammer, B., Strickert, M., & Villmann, T. (2005). On the generalization ability of GRLVQ networks. Neural Processing Letters. 21(2), 109-120. https://doi.org/10.1007/s11063-004-1547-1