基于模糊RBF神经网络的函数逼近

Fuzzy RBF Neural Network Based Function Approximation

提出了一种模糊RBF网络，将模糊逻辑的知识表达以及推理能力和RBF网络的快速学习和泛化能力结合起来，网络结构参数可按实际问题调整，仿真表明网络具有较快的学习速度和较高的函数逼近精度。

In this paper we present a fuzzy RBF neural network in which the knowledge expression of fuzzy logic is combined with fast learning speed and generalization of RBF neural network. Its structure and parameters can be adjusted according to the real problem. Simulation shows its fast learning speed and approximation accuracy.