摘要
在模糊神经网络结构的设计中,对模糊规则数目的获取,传统方法是凭经验来确定,这种方法复杂且难度大。本文提出通过模糊数据曲线来确定模糊规则,这样网络结构的建立只需要根据系统的输入输出数据来获得。并将其用于共面波导CPW(CoplanarW aveguide)的参数提取,试验数据表明该方法具有学习速度快,建模精度高等特点。
In the Furry-Neural Network model, the number of the Fuzzy-rule comes from experience. The paper presents a simple but effective way to determinate the model by using the Fuzzy-Data Curve so that its architecture is only related to the input-output data of the system. The results of parameter extraction from CPW show that the proposed method can provide optimal model and high learning efficiency.
出处
《微电子学与计算机》
CSCD
北大核心
2005年第3期156-158,161,共4页
Microelectronics & Computer
