Performance improvement of fuzzy RBF networks
- Authors
- Kim, K.-B.; Lee, D.-U.; Sim, K.-B.
- Issue Date
- Aug-2005
- Publisher
- SPRINGER-VERLAG BERLIN
- Citation
- ADVANCES IN NATURAL COMPUTATION, PT 1, PROCEEDINGS, v.3610, no.PART I, pp 237 - 244
- Pages
- 8
- Journal Title
- ADVANCES IN NATURAL COMPUTATION, PT 1, PROCEEDINGS
- Volume
- 3610
- Number
- PART I
- Start Page
- 237
- End Page
- 244
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/53208
- DOI
- 10.1007/11539087_29
- ISSN
- 0302-9743
1611-3349
- Abstract
- In this paper, we propose an improved fuzzy RBF network which dynamically adjusts the rate of learning by applying the Delta-bar-Delta algorithm in order to improve the learning performance of fuzzy RBF networks. The proposed learning algorithm, which combines the fuzzy C-Means algorithm with the generalized delta learning method, improves its teaming performance by dynamically adjusting the rate of learning. The adjustment of learning rate is achieved by self-generating middle-layered nodes and applying the Delta-bar-Delta algorithm to the generalized delta learning method for the learning of middle and output layers. To evaluate the learning performance of the proposed RBF network, we used 40 identifiers extracted from a container image as the training data. Our experimental results show that the proposed method consumes less training time and improves the convergence of learning, compared to the conventional ART2-based RBF network and fuzzy RBF network.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of ICT Engineering > School of Electrical and Electronics Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/53208)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.