论文部分内容阅读
提出一种新型神经元网络结构及其学习算法。这种改进型神经网络(MNN)由两个子神经网络综合构成:线性神经网络(LNN)和递归神经网络(DRNN)。该MNN网络能用于在线学习对象的动态特性,从而提供一种能提高整个控制系统性能的自适应控制实现策略。仿真结果表明所提出的新型神经元网络是有效的。
A new neural network structure and its learning algorithm are proposed. This improved neural network (MNN) is composed of two sub-neural networks: linear neural network (LNN) and recurrent neural network (DRNN). The MNN network can be used to study the dynamic characteristics of online learning objects, so as to provide an adaptive control implementation strategy that can improve the performance of the entire control system. Simulation results show that the proposed new neural network is effective.