A LEARNING ALGORITHM OF FUZZY NEURAL NETWORKS WITH TRIANGULAR FUZZY WEIGHTS

被引：138
作者：
ISHIBUCHI, H
KWON, K
TANAKA, H
机构：
[1] Department of Industrial Engineering, University of Osaka Prefecture, Osaka
来源：
FUZZY SETS AND SYSTEMS | 1995年 / 71卷 / 03期
关键词：
FUZZY NEURAL NETWORKS; FUZZY WEIGHTS; FUZZY INPUTS; FUZZY TARGETS; LEARNING ALGORITHM;
D O I：
10.1016/0165-0114(94)00281-B
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
In this paper, first we propose an architecture of fuzzy neural networks with triangular fuzzy weights. The proposed fuzzy neural network can handle fuzzy input vectors as well as real input vectors. In both cases, outputs from the fuzzy neural network are fuzzy vectors. The input-output relation of each unit of the fuzzy neural network is defined by the extension principle of Zadeh. Next we define a cost function for the level sets (i.e., a-cuts) of fuzzy outputs and fuzzy targets. Then we derive a learning algorithm from the cost function for adjusting three parameters of each triangular fuzzy weight. Finally, we illustrate our approach by computer simulations on numerical examples.
引用
收藏
页码：277 / 293
页数：17
相关论文
共 11 条
[1]  
Alefeld G., 1983, INTRO INTERVAL COMPU
[2]  
BUCKLEY JJ, 1991, FUZZY SETS SYSTEMS, V66, P1
[3]   FUZZY NEURAL NETWORK WITH FUZZY SIGNALS AND WEIGHTS [J].
HAYASHI, Y ;
BUCKLEY, JJ ;
CZOGALA, E .
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, 1993, 8 (04) :527-537
[4]  
Ishibuchi H., 1993, IEEE Transactions on Fuzzy Systems, V1, P85, DOI 10.1109/91.227388
[5]  
ISHIBUCHI H, 1993, 1993 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, P1650, DOI 10.1109/ICNN.1993.298804
[6]  
ISHIBUCHI H, 1994, J APPROX REASON, V10, P3
[7]  
ISHIBUCHI H, 1992, 1992 P FUZZ IEEE 92, P643
[8]  
Rumelhart DE, 1986, ENCY DATABASE SYST, P45
[9]   CONCEPT OF A LINGUISTIC VARIABLE AND ITS APPLICATION TO APPROXIMATE REASONING .2. [J].
ZADEH, LA .
INFORMATION SCIENCES, 1975, 8 (04) :301-357
[10]   CONCEPT OF A LINGUISTIC VARIABLE AND ITS APPLICATION TO APPROXIMATE REASONING .3. [J].
ZADEH, LA .
INFORMATION SCIENCES, 1975, 9 (01) :43-80
12