
For FullText PDF, please login, if you are a member of IEICE,
or go to Pay Per View on menu list, if you are a nonmember of IEICE.

An Adaptive Learning and SelfDeleting Neural Network for Vector Quantization
Michiharu MAEDA Hiromi MIYAJIMA Sadayuki MURASHIMA
Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Vol.E79A
No.11
pp.18861893 Publication Date: 1996/11/25 Online ISSN:
DOI: Print ISSN: 09168508 Type of Manuscript: PAPER Category: Nonlinear Problems Keyword: selforganizing neural networks, adaptive learning, deleting algorithm, vector quantization, mean square error,
Full Text: PDF(1.1MB)>>
Summary:
This paper describes an adaptive neural vector quantization algorithm with a deleting approach of weight (reference) vectors. We call the algorithm an adaptive learning and selfdeleting algorithm. At the beginning, we introduce an improved topological neighborhood and an adaptive vector quantization algorithm with little depending on initial values of weight vectors. Then we present the adaptive learning and selfdeleting algorithm. The algorithm is represented as the following descriptions: At first, many weight vectors are prepared, and the algorithm is processed with Kohonen's selforganizing feature map. Next, weight vectors are deleted sequentially to the fixed number of them, and the algorithm processed with competitive learning. At the end, we discuss algorithms with neighborhood relations compared with the proposed one. The proposed algorithm is also good in the case of a poor initialization of weight vectors. Experimental results are given to show the effectiveness of the proposed algorithm.

