论文部分内容阅读
在径向基函数神经网络 (RBFNN)和递归神经网络 (RNN)的基础上 ,提出了一类新的递归径向基函数神经网络 (RRBFNN)模型 ,它具有两种网络模型的优点 .文中对它的渐近稳定性和学习算法进行了研究 ,并给出相关的定理和公式 .仿真结果表明了该神经网络模型在控制不稳定非线性系统 (如小车 倒摆系统 )具有巨大潜力 .
Based on Radial Basis Function Neural Network (RBFNN) and Recurrent Neural Network (RNN), a new class of recursive radial basis function neural networks (RRBFNN) model is proposed, which has the advantages of two network models. Its asymptotic stability and learning algorithm are studied, and some related theorems and formulas are given.The simulation results show that the neural network model has great potential in controlling unstable nonlinear systems such as dolly-down system.