Sparse functional relevance learning in generalized learning vector quantization

Authors:
Thomas Villmann;Marika Kästner
Affiliations:
University of Applied Sciences Mittweida, Dep. of Mathematics, Natural and Computer Sciences, Mittweida, Germany;University of Applied Sciences Mittweida, Dep. of Mathematics, Natural and Computer Sciences, Mittweida, Germany
Venue:
WSOM'11 Proceedings of the 8th international conference on Advances in self-organizing maps
Year:
2011

Citing 4
Cited 0

Self-organizing maps

Self-organizing maps
Generalized relevance learning vector quantization

Neural Networks - New developments in self-organizing maps
Nonlinear Dimensionality Reduction

Nonlinear Dimensionality Reduction
Divergence-based vector quantization

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a functional relevance learning for learning vector quantization of functional data. The relevance profile is taken as a superposition of a set of basis functions depending on only a few parameters compared to standard relevance learning. Moreover, the sparsity of the superposition is achieved by an entropy based penalty function forcing sparsity.