Browse > Article

ART1-based Fuzzy Supervised Learning Algorithm  

Kim Kwang-Baek (신라대학교 컴퓨터공학과)
Cho Jae-Hyun (부산가톨릭대학교 컴퓨터정보공학부)
Abstract
Error backpropagation algorithm of multilayer perceptron may result in local-minima because of the insufficient nodes in the hidden layer, inadequate momentum set-up, and initial weights. In this paper, we proposed the ART-1 based fuzzy supervised learning algorithm which is composed of ART-1 and fuzzy single layer supervised learning algorithm. The Proposed fuzzy supervised learning algorithm using self-generation method applied not only ART-1 to creation of nodes from the input layer to the hidden layer, but also the winer-take-all method, modifying stored patterns according to specific patterns. to adjustment of weights. We have applied the proposed learning method to the problem of recognizing a resident registration number in resident cards. Our experimental result showed that the possibility of local-minima was decreased and the teaming speed and the paralysis were improved more than the conventional error backpropagation algorithm.
Keywords
ART-1; Fuzzy single layer supervised learning algorithm; Winner-take-all method; Paralysis;
Citations & Related Records
연도 인용수 순위
  • Reference
1 R. A. Jacobs, 'Increased rates of convergence through learning rate adaptation,' Neural Networks, Vol.1, No.4, pp.295-308, 1988
2 K. B. Kim, S. W. Jang and C. K. Kim, 'Recognition of Car License Plate by Using Dynamical Thresholding Method and Enhanced Neural Networks,' Lecture Notes in Computer Science, LNCS 2756, pp.309-319, 2001
3 K. B. Kim and K. C. Kim 'A Study on Face Recognition using New Fuzzy ART,' Proceedings of ITC-CSCC, Vol.2, pp.1057 -1060, 1998
4 K. B. Kim, M. H. Kang and E. Y. Cha, 'Fuzzy Competitive Backpropagation using Nervous System,' Proceedings of WCSS, pp.188-193, 1997
5 M. Georipoulos, G. L. Heileman and J. Huang, Properties of Learning Related to Pattern Diversity in ARTl,' Neural Networks, Vol.4, pp.751-757, 1991   DOI   ScienceOn
6 A. James and Freeman, Neural Networks : Algorithm, Application . and Programming Techniques, Addison-Wesley, 1991
7 R. Hecht-Nielsen, 'Theory of Backpropag- ation Neural Networks,' Proceedings of IJCNN, Yol.1, pp.593-605, 1989
8 Y. Hayashi, E. Czogala and J. J. Buckley,' Fuuzy Neural Controller,' Proceedings of IEEE Fuzzy Systems, pp.197-202, Vol.1, 1992
9 K. B. Kim, Y. H. Joo, J. H. Cho, 'An Enhanced Fuzzy Neural Network,' Lecture Notes in Computer Science, LNCS 3320, pp.176-179, 2004