一种算法改进的模糊神经网络及其性能分析

An Fuzzy Neural Network of Improved Algorithm and Its Performance Analysis

将T-S模糊模型与前馈神经网络相融合构造了一种新型的模糊神经网络,该模型采用基于梯度下降法和算法相结合的混合学习方法,其中梯度下降法用来训练高斯型隶属度函数的非线性参数,而算法用来训练线性参数,即权值。从理论上,证明了该模型对非线性函数的万能逼近能力。仿真实验表明,该模糊神经网络用于非线性动态系统辨识的有效性。

Based on the combination of T-S fuzzy model and the feedforward neural networks, this paper researches a new model, called fuzzy neural network, and research a mixed learning algorithm based on the combination of gradient descent algorithm and algorithm. Here, the nonlinear parameters are learned by gradient descent algorithm and linear parameters, viz., weights are learned by algorithm. The approximation capabilities of the model to nonlinear function are theoretically proved. Finally, the effectiveness of the proposed technique is confirmed by the simulation results of nonlinear system identification.