关键词: 人工智能, 细胞神经网络, 全局渐近稳定, 多时变时滞, 线性矩阵不等式, Lyapunov-Krasovskii泛函

Abstract: The global asymptotic stability was discussed for the cellular neural networks(CNN) with multiple timevarying delays. Several new sufficient criteria were given to ascertain the uniqueness and the global asymptotic stability of the equilibrium point for the CNN with multiple timevarying delays. The studied neural networks model expands the existing equivalent models, and the new criteria generalize and improve upon some previous ones. Moreover, the obtained criteria eliminate the effects caused by the neuronal excitatory and the inhibitory, can be expressed in the form of linear matrix inequality, and is easily verified using the recently developed interiorpoint algorithms. Two remarks were presented to demonstrate the effectiveness and features of the new stability criteria.

Key words: artificial intelligence, cellular neural networks (CNN), global asymptotic stability, multiple timevarying delays, linear matrix inequality, LyapunovKrasovskii-functional