一种改进的RBF网络结构及其参数的设计方法

针对神经网络在学习之后,模糊系统的原始结构被改变,或削弱了规则可解释性这一模糊系统突出特点的问题,给出了一种提取模糊If-then规则的径向基函数(RBF)神经网络结构。该神经网络结构具有能够同时清晰表达模糊控制系统输入空间划分和模糊规则可解释性的特点,克服了以往用神经网络提取模糊规则不能直观体现模糊语言规则可解释性的不足,并详细地讨论了此网络结构参数的设计方法。

Improved RBF Neural Network and Design of Its Parameters

The learning algorithms developed in the field of artificial neural networks can be used to adjust the parameters of fuzzy systems.But after the neural network learning,the structure of the original fuzzy system is changed and the interpretability,which is considered to be one of the most important features of fuzzy system,is usually impaired.An improved fuzzy-neural network structure and a design of each layer are proposed.The RBF neural network not only expresses the architecture of fuzzy systems clearly,but also maintains the explanative characteristic of linguistic meaning.