For Full-Text 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.
Competitive Learning Algorithms Founded on Adaptivity and Sensitivity Deletion Methods
Michiharu MAEDA Hiromi MIYAJIMA
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2000/12/25
Print ISSN: 0916-8508
Type of Manuscript: LETTER
Category: Neural Networks and Bioengineering
competitive learning, neural networks, deleting mechanism, vector quantization,
Full Text: PDF(306.3KB)>>
This paper describes two competitive learning algorithms from the viewpoint of deleting mechanisms of weight (reference) vectors. The techniques are termed the adaptivity and sensitivity deletions participated in the criteria of partition error and distortion error, respectively. Experimental results show the effectiveness of the proposed approaches in the average distortion.