Fuzzy logic systems are equivalent to feedforward neural networks

被引:0
作者
Hongxing Li
机构
[1] Beijing Normal University,Department of Mathematics
来源
Science in China Series E: Technological Sciences | 2000年 / 43卷
关键词
fuzzy logic systems; neural networks; feedforward neural networks; interpolation representation; rectangle wave neural networks; nonlinear neural networks; linear neural networks;
D O I
暂无
中图分类号
学科分类号
摘要
Fuzzy logic systems and feedforward neural networks are equivalent in essence. First, interpolation representations of fuzzy logic systems are introduced and several important conclusions are given. Then three important kinds of neural networks are defined, i. e. linear neural networks, rectangle wave neural networks and nonlinear neural networks. Then it is proved that nonlinear neural networks can be represented by rectangle wave neural networks. Based on the results mentioned above, the equivalence between fuzzy logic systems and feedforward neural networks is proved, which will be very useful for theoretical research or applications on fuzzy logic systems or neural networks by means of combining fuzzy logic systems with neural networks.
引用
收藏
页码:42 / 54
页数:12
相关论文
共 6 条
[1]  
Hongxing Li(1998)Interpolation mechanism of fuzzy control Science in China, Ser. E 41 312-312
[2]  
Hongxing Li(1990)Multifactorial functions in fuzzy sets theory Fuzzy Sets and Systems 35 69-69
[3]  
Naiyao Zhang(1997)Structure analysis of typical fuzzy controllers Fuzzy Systems and Mathematics 11 10-10
[4]  
Mizumoto M.(1990)The improvement of fuzzy control algorithm, part 4: (+, ·)-centroid algorithm Proceedings of Fuzzy Systems Theory 6 9-9
[5]  
Takagi T.(1985)Fuzzy identification of systems and its applications to modeling and control IEEE Trans. Syst. Man and Cybern. 15 1-1
[6]  
Sugeno M.(undefined)undefined undefined undefined undefined-undefined