Title :
Novel global exponential stability condition for discrete-time recurrent neural networks with random time-varying delays:
Author :
Fattahi, Maryarn ; Momeni, Harnidreza
Author_Institution :
Electr. Eng. Dept., Tarbiat Modares Univ., Tehran, Iran
Abstract :
In this paper, problem of stability for a class of discrete-time recurrent neural networks (DRNNs) with time-varying delay is considered. By employing the Lyapunov-Krasovskii function, a new condition for stability of time-delayed system is proposed. Result developed is in the term of linear matrix inequality (LMI) which can be easily checked by LMI Control toolbox. Furthermore, numerical examples are given to confirm the validity of the obtained approach.
Keywords :
Lyapunov methods; asymptotic stability; delays; linear matrix inequalities; neural nets; random processes; time-varying systems; DRNN; Lyapunov-Krasovskii function; discrete-time recurrent neural networks; global exponential stability; linear matrix inequality; random time-varying delays; time-delayed system; Power capacitors; Lyapunov-Krasovskii function; discrete-time recurrent neural networks; linear matrix inequality;
Conference_Titel :
Biomedical Engineering (ICBME), 2010 17th Iranian Conference of
Conference_Location :
Isfahan
Print_ISBN :
978-1-4244-7483-7
DOI :
10.1109/ICBME.2010.5705031
