西南交通大学学报(英文版)2003，Vol.11Issue(1)：16-22,7.
Additive-Multiplicative Fuzzy Neural Network and Its Performance
Additive-Multiplicative Fuzzy Neural Network and Its Performance
翟东海 1靳蕃1
作者信息
- 1. School of Computer and Communication Engineering, Southwest Jiaotong University, Chengdu 610031, China
- 折叠
摘要
Abstract
In view of the main weaknesses of current fuzzy neural networks such as low reasoning precision and long training time, an Additive-Multiplicative Fuzzy Neural Network (AMFNN) model and its architecture are presented. AMFNN combines additive inference and multiplicative inference into an integral whole, reasonably makes use of their advantages of inference and effectively overcomes their weaknesses when they are used for inference separately. Here, an error back propagation algorithm for AMFNN is presented based on the gradient descent method. Comparisons between the AMFNN and six representative fuzzy inference methods shows that the AMFNN is characterized by higher reasoning precision, wider application scope, stronger generalization capability and easier implementation.关键词
fuzzy inference/additive-multiplicative fuzzy neural network/fuzzy rule acquisitionKey words
fuzzy inference/additive-multiplicative fuzzy neural network/fuzzy rule acquisition分类
信息技术与安全科学引用本文复制引用
翟东海,靳蕃..Additive-Multiplicative Fuzzy Neural Network and Its Performance[J].西南交通大学学报(英文版),2003,11(1):16-22,7.
