论文部分内容阅读
In this paper, the normalized exponential neural network (ENN) is studied. It is proved that ENN is a universal approximator. The stability relation between systems and neural networks working as controllers is investigated. The results show that when designing a system, one should firstly consider system stability rather than controller stability. Accordingly, a new hybrid learning algorithm is presented, and it is proved that this algorithm eventually converge to equilibria.
In this paper, the normalized exponential neural network (ENN) is studied. It is demonstrated that ENN is a universal approximator. The stability relation between systems and neural networks working as controllers is investigated.先 consider system stability rather than controller stability.., a new hybrid learning algorithm is presented, and it is verified that this algorithm eventually converge to equilibria.