Distance Learning in Discriminative Vector Quantization
- 1 October 2009
- journal article
- Published by MIT Press in Neural Computation
- Vol. 21 (10) , 2942-2969
Abstract
Discriminative vector quantization schemes such as learning vector quantization (LVQ) and extensions thereof offer efficient and intuitive classifiers based on the representation of classes by prototypes. The original methods, however, rely on the Euclidean distance corresponding to the assumption that the data can be represented by isotropic clusters. For this reason, extensions of the methods to more general metric structures have been proposed, such as relevance adaptation in generalized LVQ (GLVQ) and matrix learning in GLVQ. In these approaches, metric parameters are learned based on the given classification task such that a data-driven distance measure is found. In this letter, we consider full matrix adaptation in advanced LVQ schemes. In particular, we introduce matrix learning to a recent statistical formalization of LVQ, robust soft LVQ, and we compare the results on several artificial and real-life data sets to matrix learning in GLVQ, a derivation of LVQ-like learning based on a (heuristic) cost function. In all cases, matrix adaptation allows a significant improvement of the classification accuracy. Interestingly, however, the principled behavior of the models with respect to prototype locations and extracted matrix dimensions shows several characteristic differences depending on the data sets.Keywords
This publication has 6 references indexed in Scilit:
- Matrix Learning for Topographic Neural Maps2008
- Analysis of Tiling Microarray Data by Learning Vector Quantization and Relevance Learning2007
- On the Generalization Ability of GRLVQ NetworksNeural Processing Letters, 2005
- Soft Learning Vector QuantizationNeural Computation, 2003
- Generalized relevance learning vector quantizationNeural Networks, 2002
- Self-Organizing Maps1997