Novel stability criterions for two types of recurrent neural networks with time-varying delays

作者：Luo, Wenguang; Liu, Yonghua; Xie, Guangming; Lan, Hongli

来源：Control and Intelligent Systems, 2014, 42(3): 191-200.

DOI：10.2316/Journal.201.2014.3.201-2510

• Discrete and distributed delays
• Global asymptotic stability
• Globally exponential stability
• Lyapunov-krasovskii functional (LKF)
• Lyapunov-Krasovskii functionals
• Recurrent neural network (RNNs)
• Stochastic fuzzy cellular neural networks
• Stochastic stability theory

This paper discusses the stability problems about two types of recurrent neural networks (RNNs) with time-varying delays. By applying the linear matrix inequality (LMI) and Lyapunov-Krasovskii functional (LKF), the novel sufficient condition of globally exponential stability for RNNs with time-varying discrete and distributed delays is derived under the condition of the more general activation function. The new mean-square global asymptotic stability criterion for stochastic fuzzy cellular neural networks (SFCNNs) with timevarying delays is also derived by constructing a new LKF and using Ito's stochastic stability theory. The obtained results are helpful to design the stability of above two systems. Finally, some illustrative examples are given to verify the feasibility and effectiveness of the results.

• 出版日期2014-8-11
• 单位华东师范大学; 北京大学; RMIT university; RMIT University; 广西大学; 清华大学; 华南理工大学