IEEE Trans Neural Netw Learn Syst. 2017 Mar;28(3):766-771. doi: 10.1109/TNNLS.2015.2513001. Epub 2016 Jan 6.
In this brief, we establish a novel complex-valued memristive recurrent neural network (CVMRNN) to study its stability. As a generalization of real-valued memristive neural networks, CVMRNN can be separated into real and imaginary parts. By means of M -matrix and Lyapunov function, the existence, uniqueness, and exponential stability of the equilibrium point for CVMRNNs are investigated, and sufficient conditions are presented. Finally, the effectiveness of obtained results is illustrated by two numerical examples.
在这份简介中，我们建立了一个新的复值忆阻递归神经网络 (CVMRNN) 来研究其稳定性。作为实值忆阻神经网络的推广，CVMRNN 可以分为实部和虚部。通过 M-矩阵和李雅普诺夫函数，研究了 CVMRNN 的平衡点的存在性、唯一性和指数稳定性，并给出了充分条件。最后，通过两个数值例子说明了所得结果的有效性。
