Exponential Stability on Stochastic Neural Networks With Discrete Interval and Distributed Delays

• Published in: IEEE transaction on neural networks and learning systems 2010-01, Vol.21 (1), p.169-175
• Main Authors: Yang, Rongni, Zhang, Zexu, Shi, Peng
• Format: Article
• Language: English
• Subjects: Applied sciences; Artificial intelligence; Computer science; control theory; systems; Computer Simulation; Connectionism. Neural networks; Criteria; Delay; Delay effects; Delay partitioning; Exact sciences and technology; exponential stability; Humans; Information Storage and Retrieval; interval time-varying delay; Intervals; Linear matrix inequalities; Lower bounds; Neural networks; Neural Networks (Computer); Neurotransmitters; Nonlinear Dynamics; Partitioning; Signal processing; Space technology; Stability; Stability analysis; Stability criteria; stochastic neural networks (SNNs); Stochastic Processes; Stochastic systems; Stochasticity; Time Factors
• ISSN: 1045-9227; 2162-237X; 1941-0093; 2162-2388
• DOI: 10.1109/TNN.2009.2036610

This brief addresses the stability analysis problem for stochastic neural networks (SNNs) with discrete interval and distributed time-varying delays. The interval time-varying delay is assumed to satisfy 0 < d 1 ¿ d(t) ¿ d 2 and is described as d ( t ) = d 1 + h ( t ) with 0 ¿ h ( t ) ¿ d 2 - d 1 . Based on the idea of partitioning the lower bound d 1 , new delay-dependent stability criteria are presented by constructing a novel Lyapunov-Krasovskii functional, which can guarantee the new stability conditions to be less conservative than those in the literature. The obtained results are formulated in the form of linear matrix inequalities (LMIs). Numerical examples are provided to illustrate the effectiveness and less conservatism of the developed results.