On the Generalization Ability of GRLVQ Networks
作者:Barbara Hammer, Marc Strickert, Thomas Villmann
摘要
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].
论文关键词:adaptive metric, generalization bounds, LVQ, margin optimization, relevance LVQ
论文评审过程:
论文官网地址:https://doi.org/10.1007/s11063-004-1547-1