New stability criteria for recurrent neural networks with interval time-varying delay

• Published in: Neurocomputing (Amsterdam) Vol. 121; pp. 179 - 184
• Main Authors: Bai, Yong-Qiang, Chen, Jie
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 09.12.2013; Elsevier
• Subjects: Applied sciences; Artificial intelligence; Computer science; control theory; systems; Connectionism. Neural networks; Criteria; Delay; Delay-dependent stability; Exact sciences and technology; Inequalities; Integrals; Interval time-varying delay; Intervals; Linear matrix inequality; Mathematical models; Recurrent neural network; Recurrent neural networks; Stability; Linear matrix inequality; Interval time-varying delay; Recurrent neural network; Delay-dependent stability; Recurrence; Recurrent neural nets; Stability; Lyapunov method; Delay system; Stability criterion; Neural network; Convex programming; Delay; Time varying system; Efficiency; Integral equation; Time interval; Delay time; Lyapunov function
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2013.04.031

This paper is concerned with the problem of stability analysis of recurrent neural networks with time-varying delay belonging to a given interval. By constructing a novel augmented Lyapunov functional which contains some triple-integral terms, improved delay-dependent stability criteria are derived in terms of linear matrix inequality (LMI) by introducing some free-weighting matrices and using integral inequality technique and convex combination method. Numerical examples are given to illustrate the effectiveness of the proposed method. •A new Lyapunov functional containing triple-integral terms is proposed.•Some less conservative stability conditions are obtained.•The proposed method involves fewer decision variables than free-weighting matrices method.