Global stability results of discrete recurrent neural networks with interval delays

作者：Mahmoud Magdi S^*; Al Sunni Fouad M

来源：IMA Journal of Mathematical Control and Information, 2012, 29(2): 199-213.

DOI：10.1093/imamci/dnr034

• recurrent neural networks
• discrete-time systems
• time-varying delays
• delay-range-dependent stability
• LMIs

This paper establishes improved global exponential stability method for a class of discrete-time recurrent neural networks with interval time-varying delays and norm-bounded time-varying parameter uncertainties. The method is robust and delay range dependent. It is derived based on a new Lyapunov-Krasovskii functional constructed to exhibit the delay-dependent dynamics and to compensate for the enlarged time span. The developed stability method eliminates the need for over bounding and utilizes smaller number of linear matrix inequality (LMI) decision variables. New and less conservative solutions to the global stability problem are provided in terms of feasibility testing of new parameterized LMIs. Numerical examples are presented to illustrate the effectiveness of the developed technique.

• 出版日期2012-6
• 单位中国石油大学（北京）