Summary
|
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. |
|
Enhanced RBF Network by Using ART2 Algorithm and Fuzzy Control Method Kwang-Baek KIM Sung-Kwan JE Young-Ju KIM Publication IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences Vol.E88-A No.6 pp.1497-1501 Publication Date: 2005/06/01 Online ISSN: DOI: 10.1093/ietfec/e88-a.6.1497 Print ISSN: 0916-8508 Type of Manuscript: Special Section LETTER (Special Section on Papers Selected from 2004 International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC 2004)) Category: Keyword: enhanced RBF network, ART2 network, learning rate, momentum, fuzzy control system, delta-bar-delta, Full Text: PDF(141.9KB)>>
Summary: This paper proposes an enhanced RBF network that enhances learning algorithms between input layer and middle layer and between middle layer and output layer individually for improving the efficiency of learning. The proposed network applies ART2 network as the learning structure between input layer and middle layer. And the auto-tuning method of learning rate and momentum is proposed and applied to learning between middle layer and output layer, which arbitrates learning rate and momentum dynamically by using the fuzzy control system for the arbitration of the connected weight between middle layer and output layer. The experiment for the classification of number patterns extracted from the citizen registration card shows that compared with conventional networks such as delta-bar-delta algorithm and the ART2-based RBF network, the proposed method achieves the improvement of performance in terms of learning speed and convergence. | ||||||||||
| ||||||||||
