Browse > Article
http://dx.doi.org/10.9708/jksci.2014.19.9.033

A Hybrid RBF Network based on Fuzzy Dynamic Learning Rate Control  

Kim, Kwang-Baek (Dept. of Computer Engineering, Silla University)
Park, Choong-Shik (Dept. of Smart IT, Youngdong University)
Abstract
The FCM based hybrid RBF network is a heterogeneous learning network model that applies FCM algorithm between input and middle layer and applies Max_Min algorithm between middle layer and output. The Max-Min neural network uses winner nodes of the middle layer as input but shows inefficient learning in performance when the input vector consists of too many patterns. To overcome this problem, we propose a dynamic learning rate control based on fuzzy logic. The proposed method first classifies accurate/inaccurate class with respect to the difference between target value and output value with threshold and then fuzzy membership function and fuzzy decision logic is designed to control the learning rate dynamically. We apply this proposed RBF network to the character recognition problem and the efficacy of the proposed method is verified in the experiment.
Keywords
FCM based hybrid network; Max-Min neural network; Fuzzy logic; Learning rate;
Citations & Related Records
연도 인용수 순위
  • Reference
1 D. K. Arun, Computer Vision and Fuzzy-Neural Systems, Prentice Hall PTR, 2001.
2 D. Q Zhang, S. C. Chen, "Clustering Incomplete Data Using Kernel-Based Fuzzy C-means Algorithm," Neural Processing Letters, Vol.18, Issue 3, pp.155-162, 2003.   DOI
3 L. S. Hsu, et als, "Fuzzy Neural-Logic System", Proceedings of IJCNN, Vol.1, pp.254-250, 1992.
4 A. Blanco, N. Delgado, I. Requena, "Solving fuzzy relational equations by max-min neural networks," Proceedings of IEEE World Congress on Computational Intelligence, Vol. 3, pp.1737 - 1742, 1994.
5 K. B. Kim, M. H. Kang, E. Y. Cha, "A Fuzzy Competitive Backpropagation using Nervous System," Proceedings of World Congress on Systems Simulation, pp.188-193, 1997.
6 K. B. Kim, Y. H. Joo, J. H. Cho, "An Enhanced Fuzzy Neural Network, Lecture Notes in Computer Science, Vol. 3320, pp.176-179, 2005.
7 K. B. Kim, S. Kim, "Hierarchical Recognition of English Calling Card by Using Multiresolution Images and Enhanced Neural Network," Lecture Notes in Computer Science, Vol. 3801, pp.785-792, 2005.
8 K. B. Kim, A. S. Oh, Y. W. Woo, "Enhanced FCM-based Hybrid Network," INFORMATION-AN INTERNATIONAL INTERDISCIPLINARY JOURNAL, Vol.16, No. 2B, pp.1509-1515, 2013.
9 K. B. Kim, C. K. Kim, "Performance Improvement of RBF Network using ART2 Algorithm and Fuzzy Logic System," Lecture Notes in Artificial Intelligence, LNAL 3339, Springer, pp.853-860, 2004.