Browse > Article
http://dx.doi.org/10.6109/jkiice.2007.11.7.1387

An Enhanced Fuzzy Single Layer Perceptron With Linear Activation Function  

Park, Choong-Shik (영동대학교 컴퓨터공학과)
Cho, Jae-Hyun (부산가톨릭대학교 컴퓨터공학과)
Kim, Kwang-Baek (신라대학교 컴퓨터정보공학부)
Abstract
Even if the linearly separable patterns can be classified by the conventional single layer perceptron, the non-linear problems such as XOR can not be classified by it. A fuzzy single layer perceptron can solve the conventional XOR problems by applying fuzzy membership functions. However, in the fuzzy single layer perception, there are a couple disadvantages which are a decision boundary is sometimes vibrating and a convergence may be extremely lowered according to the scopes of the initial values and learning rates. In this paper, for these reasons, we proposed an enhanced fuzzy single layer perceptron algorithm that can prevent from vibration the decision boundary by introducing a bias term and can also reduce the learn time by applying the modified delta rule which include the learning rates and the momentum concept and applying the new linear activation function. Consequently, the simulation results of the XOR and pattern classification problems presented that the proposed method provided the shorter learning time and better convergence than the conventional fuzzy single layer perceptron.
Keywords
XOR;
Citations & Related Records
연도 인용수 순위
  • Reference
1 K. B. Kim, M. H. Kang and E. Y. Cha, 'A Fuzzy Competitive Backpropagation using Nervous System,' in Proc. WCSS, pp.188-193, 1997
2 Marin T. Hagan, Howard B. Demuth, Mark Beale, Neural Network Design, PWS Publishing, Boston, 1995
3 M. M. Gupta and J. Qi, On Fuzzy Neuron Models,' Proceedings of IJCNN, Vol.2, pp.431-435, 1991
4 K. B. Kim, B. K. Lee, S. H. Kim, 'Enhanced Fuzzy Single Layer Learning Algorithm using Automatic Tuning of Threshold,' Lecture Notes in Computer Science, LNCS 3982, Springer, pp.172-177, 2006
5 J. B. Kiszaka, M. M. Gupta, 'Fuzzy Logic Neural Network,' BUSFAL, No.4, 1990
6 T. H. Goh, P. Z. Wang and H. C. Lui, Learning Algorithm for Enhanced Fuzzy Perceptron,' Proceedings of IJCNN, Vol.2, pp.435-440, 1992
7 R. Hecht-Nielsen, 'Theory of Back- propagation Neural Networks,' Proc. of UCNN, Vol.1, pp.593-605, 1989