ISSN:
1573-773X
Content:
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]. Keywords adaptive metric - generalization bounds - LVQ - margin optimization - relevance LVQ
In:
Neural processing letters, Dordrecht [u.a.] : Springer Science + Business Media B.V, 1994, 21(2005), 2, Seite 109-120, 1573-773X
In:
volume:21
In:
year:2005
In:
number:2
In:
pages:109-120
Language:
English
Author information:
Hammer, Barbara 1970-
Bookmarklink