English  |  正體中文  |  简体中文  |  Items with full text/Total items : 26988/38789
Visitors : 2346208      Online Users : 28
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search
LoginUploadHelpAboutAdminister

Please use this identifier to cite or link to this item: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/50965

Title: Online learning vector quantization: a harmonic competition approach based on conservation network
Authors: Jung-Hua Wang
Wei-Der Sun
Contributors: 國立臺灣海洋大學電機工程學系
Keywords: Vector quantization
Neural networks
Sun
Biological information theory
Systematics
Oceans
Training data
Convergence
Density functional theory
Euclidean distance
Date: 1999-10
Issue Date: 2018-11-02T01:06:46Z
Publisher: IEEE Trans. on Systems, Man, and Cybernetics-Part B
Abstract: Abstract: This paper presents a self-creating neural network in which a conservation principle is incorporated with the competitive learning algorithm to harmonize equi-probable and equi-distortion criteria. Each node is associated with a measure of vitality which is updated after each input presentation. The total amount of vitality in the network at any time is 1, hence the name conservation. Competitive learning based on a vitality conservation principle is near-optimum, in the sense that problem of trapping in a local minimum is alleviated by adding perturbations to the learning rate during node generation processes. Combined with a procedure that redistributes the learning rate variables after generation and removal of nodes, the competitive conservation strategy provides a novel approach to the problem of harmonizing equi-error and equi-probable criteria. The training process is smooth and incremental, it not only achieves the biologically plausible learning property, but also facilitates systematic derivations for training parameters. Comparison studies on learning vector quantization involving stationary and nonstationary, structured and nonstructured inputs demonstrate that the proposed network outperforms other competitive networks in terms of quantization error, learning speed, and codeword search efficiency.
Relation: 29(5) pp.642-653
URI: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/50965
Appears in Collections:[電機工程學系] 期刊論文

Files in This Item:

File Description SizeFormat
index.html0KbHTML15View/Open


All items in NTOUR are protected by copyright, with all rights reserved.

 


著作權政策宣告: 本網站之內容為國立臺灣海洋大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,請合理使用本網站之內容,以尊重著作權人之權益。
網站維護: 海大圖資處 圖書系統組
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback