【摘要】 泛函网络是最近提出的一种对神经网络的有效推广。与神经网络不同 ,它处理的是一般的泛函模型 ,而不仅仅是Sigmoidal函数 ,并且在各个处理单元之间没有权值。提出了一种基于泛函网络的非线性系统的辨识方法 ,而网络参数利用梯度下降方法来进行学习。计算机仿真结果表明 ,这种辨识方法具有较快的收敛速度和良好的性能。更多还原

【Abstract】 Functional network is a recently introduced extension of neural networks. Unlike neural networks, it deals with general functional models instead of sigmoid-like ones. And in these networks there are no weights associated with the links connecting neurons. In this paper, we propose a functional network method for the identification of nonlinear systems. And the learning of parameters of the functional networks is carried out by the gradient descent algorithm. The simulation results demonstrate that the identification method presented in the paper has rapid convergence speed and powerful performance.更多还原