摘要
本文将模糊C均值聚类和自适应神经模糊网络结合起来。模糊C均值聚类用于对输入变量空间进行划分,生成初始的模糊规则库,自适应模糊神经网络(ANFIS)选用最小二乘法和BP算法。与普通的模糊神经网络相比,这种模糊神经网络收敛速度快,建模精度高。
A hybrid approach for fuzzy system design based on fuzzy clustering and a kind of fh^y neural networks. Firstly, Fuzzy clustering is used to divide fuzzy space and generate initial fuzzy rules from the given input data. Secondly, Adaptive-Network based Fuzzy Inference System（ANFIS） turn parameters by means of least-square methods and gradient descent methods. Simulations results show that this method has better generalization and approximation abilities.
出处
《石家庄铁路职业技术学院学报》
2005年第3期29-32,共4页
Journal of Shijiazhuang Institute of Railway Technology
关键词
模糊神经网络
模糊聚类
fuzzy neural network fuzzy clustering
