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].
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Anguita, D., Ridella, S., Rivieccio, F. and Zunino, R.: Automatic hyperparameter tuning for support vector machines. In: J. R. Dorronsoro (ed.), ICANN 2002, pp. 1345–1350, Springer, 2002.
P. L. Bartlett S. Mendelson (2002) ArticleTitleRademacher and Gaussian complexities: risk bounds and structural results J Mach Learn Res 3 463–482
J.C. Bezdek (1981) Pattern Recognition with Fuzzy Objective Function Algorithms. Plenum Press New York
Bojer, T., Hammer, B., Schunk, D. and Tluk von Toschanowitz, K.: Relevance determination in learning vector quantization. In: Proc. of European Symposium on Artificial Neural Networks (ESANN’01), pp. 271–276, Brussels, Belgium, 2001. D facto publications.
Bousquet, O. and Herrmann, D. J. L.: On the complexity of learning the kernel matrix. In: Advances in Neural Information Processing Systems 2002, to appear.
Neural Networks Research Centre, Otaniemi: Helsinki University of Technology. Bibliography on the self-organizing map (SOM) and learning vector quantization (LVQ). Available at: http://liinwww.ira.uka.de/bibliography/Neural/SOM.LVQ.html.
V. Cherkassky D. Gehring F. Mulier (1996) ArticleTitleComparison of adaptive methods for function estimation from samples IEEE Tr Neural Networ 7 969–984
C. Cortes V. Vapnik (1995) ArticleTitleSupport vector network Mach Learn 20 1–20
Crammer, K., Gilad-Bachrach, R., Navot, A. and Tishby, A.: Margin analysis of the LVQ algorithm. In: Advances in Neural Information Processing Systems 2002, to appear.
R. N. Davé (1990) ArticleTitleFuzzy shell-clustering and application to circle detection in digital images Int J of Gen Syst 16 343–355
I. Gath A. B. Geva (1989) ArticleTitleUnsupervised optimal fuzzy clustering IEEE Tn Pattern Anal Mach Intelligence 11 773–781
van Gestel, T., Suykens, J. A. K., de Moor, B. and Vandewalle, J.: Automatic relevance determination for least squares support vector machine classifiers. In: M. Verleysen (ed.), European Symposium on Artificial Neural Networks 2001, pp. 13–18.
Y. Grandvalet (2000) ArticleTitleAnisotropic noise injection for input variables relevance determination IEEE T Neural Networ 11 IssueID6 1201–1212
S. Günter H. Bunke (2002) ArticleTitleSelf-organizing map for clustering in the graph domain Pattern Recog Lett 23 401–417
E.E. Gustafson W.C. Kessel (1979) Fuzzy clustering with a fuzzy covariance matrix IEEE CDC San Diego, California 761–766
Hammer, B., Rechtien, A., Strickert, M., Villmann, T.: Rule extraction from self-organizing networks. In: J. R. Dorronsoro (ed.), ICANN 2002, pp. 877–882, Springer, 2002.
Hammer, B., Strickert, M. and Villmann, T.: Supervised neural gas with general similarity measure. To appear in Neural Process Lett.
Hammer, B., Strickert, M. and Villmann, T.: Prototype recognition of splice sites. In: Seiffert, U. Jain L. C. and Schweitzer P. (eds.), Bioinformatics using Computational Intelligence Paradigms, Springer, 2004, in press.
B. Hammer T. Villmann (2002) ArticleTitleGeneralized relevance learning vector quantization Neural Networks 15 1059–1068
Heskes, T.: Energy functions for self-organizing maps. In: Oja E. and Kaski S. (eds.), Kohonen Maps, pp. 303–315. Springer, 1999.
S. Kaski (2001) ArticleTitleBankruptcy analysis with self-organizing maps in learning metrics IEEE T Neural Networ 12 936–947
Kaski, S. and Sinkkonen, J.: A topography-preserving latent variable model with learning metrics. In: Allinson, N. Yin, H. Allinson L. and Slack, J. (eds.), Advances in Self-Organizing Maps, pp. 224–229, Springer, 2001.
Kohonen, T.: Learning vector quantization. In: Arbib M. (ed.), The Handbook of Brain Theory and Neural Networks, pp. 537–540. MIT Press, 1995.
Kohonen, T.: Self-Organizing Maps. Springer, 1997.
T. Kohonen P. Somervuo (2002) ArticleTitleHow to make large self-organizing maps for nonvectorial data Neural Networks 15 IssueID8–9 945–952
M. Marchand J. Shawe-Taylor (2002) ArticleTitleThe set covering machine J Mach Learn Resh 3 723–746
F. Mulier (1994) Statistical Analysis of Self-Organization University of Minnesota Minneapolis
Michie, D., Spiegelhalter, D. J. and Taylor, C. C.: (eds.), Machine Learning, Neural and Statistical Classification, Ellis Horwood, 1994.
G. Patané M. Russo (2001) ArticleTitleThe enhanced LBG algorithm Neural Networks 14 1219–1237
M. Pregenzer G. Pfurtscheller D. Flotzinger (1996) ArticleTitleAutomated feature selection with distinction sensitive learning vector quantization Neurocomputing 11 19–29
S. Ridella S. Rovetta R. Zunino (2001) ArticleTitleK-winner machines for pattern classification IEEE T Neural Networ 12 IssueID2 371–385
Sato, A. S. and Yamada, K.: Generalized learning vector quantization. In: G. Tesauro, D. Touretzky and T. Leen (eds.), Advances in Neural Information Processing Systems, Vol. 7, pp. 423–429, MIT Press, 1995.
A. S. Sato and Yamada, K.: An analysis of convergence in generalized LVQ Niklasson, L. Bodén M. and Ziemke T. (eds.), ICANN’98, pp. 172–176, Springer 1998
S. Seo K. Obermeyer (2003) ArticleTitleSoft learning vector quantization Neural computation 15 1589–1604
Strickert, M., Bojer, T. and Hammer, B.: Generalized relevance LVQ for time series. In: Dorffner, G. Bischof, H. and Hornik K. (eds.), Artificial Neural Networks - ICANN’2001, pp. 677–683, Springer, 2001.
R. Tibshirani (1996) ArticleTitleRegression shrinkage and selection via the lasso. J Ro Stat Soc Ser B 58 267–288
M. E. Tipping (2001) ArticleTitleThe relevance vector machine J Mach Lear Res 1 211–244
V. Vapnik:Statistical Learning Theory.Wiley-Interscience, 1998
V. Vapnik A. Chervonenkis (1971) ArticleTitleOn the uniform convergence of relative frequencies of events to their probabilities. Theor Probab Appl 16 IssueID2 264–280
T. Villmann B. Hammer (2003) Metric adaptation and relevance learning in learning vector quantization. Mathematik/Informatik, Universität Osnabrück
T. Villmann E. Merenyi B. Hammer (2003) ArticleTitleNeural maps in remote sensing image analysis. Neural Networks 16 IssueID(3-4) 389–403
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Hammer, B., Strickert, M. & Villmann, T. On the Generalization Ability of GRLVQ Networks. Neural Process Lett 21, 109–120 (2005). https://doi.org/10.1007/s11063-004-1547-1
Issue Date:
DOI: https://doi.org/10.1007/s11063-004-1547-1