非负放大函数与多延时的Cohen-Grossberg神经网络的鲁棒稳定性

在Cohen-Grossberg神经网络设计及实现过程中,非负放大函数条件是很实用的.在网络参数存在摄动的情况下,研究了具有非负放大函数的一类多延时Cohen-Grossberg神经网络的鲁棒渐近稳定性问题.首先通过证明一个有用的引理,建立了渐近稳定性和鲁棒稳定性之间的关系.其次,在不要求激励函数满足严格单调增加和有界性的情况下,通过构造适当的Lyapunov泛函,针对所研究的神经网络模型,基于线性矩阵不等式技术建立了平衡点鲁棒稳定的一个充分判据.仿真结果进一步证明了所得结论的有效性.

Robust Stability Analysis of Cohen-Grossberg Neural Networks with Nonnegative Amplification Function and Multiple Delays

In the process of design and implementation of Cohen-Grossberg neural networks,the nonnegative amplification function condition is very practicable.The robust asymptotic stability of a class of Cohen-Grossberg neural networks with nonnegative amplification function and multiple time delays is investigated in case of parameter perturbation.With a useful lemma proved,the relation between global asymptotic stability and robust stability is established.Then with no strictly monotonic increasing quantity and bou...