Characteristics of equinumber principle for adaptive vector quantization

Authors:
Michiharu Maeda;Noritaka Shigei;Hiromi Miyajima
Affiliations:
Kurume National College of Technology, Kurume, Japan;Faculty of Engineering, Kagoshima University, Kagoshima, Japan;Faculty of Engineering, Kagoshima University, Kagoshima, Japan
Venue:
ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part II
Year:
2005

Citing 5
Cited 0

On the stationary state of Kohonen's self-organizing sensory mapping

Biological Cybernetics
Convergence properties of Kohonen's topology conserving maps: fluctuations, stability, and dimension selection

Biological Cybernetics
Self-organization and associative memory: 3rd edition

Self-organization and associative memory: 3rd edition
Introduction to the theory of neural computation

Introduction to the theory of neural computation
Vector quantization and signal compression

Vector quantization and signal compression

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes characteristics of adaptive vector quantization according to the equinumber principle. Three methods of adaptive vector quantization are presented with the objective of avoiding the initial dependency of reference vectors. The present approaches which have output units without neighboring relations equalize the numbers of inputs in a partition space. The first approach is a creation method which sequentially creates output units to reach a predetermined number of neurons founded on the equinumber principle in the learning process. The second is a reduction method which sequentially deletes output units to reach a prespecified number. The third is an unification method of the creation and reduction methods, which deletes units after creating under the predetermined number. Experimental results show the properties of the present techniques.