Journal article
Authors list: Hammer, B; Strickert, M; Villmann, T
Publication year: 2005
Pages: 109-120
Journal: Neural Processing Letters
Volume number: 21
Issue number: 2
ISSN: 1370-4621
eISSN: 1573-773X
DOI Link: https://doi.org/10.1007/s11063-004-1547-1
Publisher: 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].
Citation Styles
Harvard Citation style: 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 Citation style: 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
