Litcius/Paper detail

Stability Analysis of Delayed Neural Networks via a Time-Varying Lyapunov Functional

Huichao Lin, Jiuxiang Dong, Hong‐Bing Zeng, Ju H. Park

2024IEEE Transactions on Systems Man and Cybernetics Systems32 citationsDOI

Abstract

This article concerns the stability issues of neural networks with time-varying delays. The purpose is to establish less conservative stability conditions for delayed neural networks. In order to achieve this goal, a time-varying Lyapunov functional method is proposed for stability analysis of delayed neural networks. The main feature of this method is to construct different Lyapunov functionals in different time-varying delay subintervals, which relaxes the restriction requirement of traditional Lyapunov functionals constructing a common Lyapunov functional in the whole delay interval. Based on the developed time-varying Lyapunov functional, some new stability conditions for delayed neural networks are obtained. Finally, two examples are given to verify the effectiveness of the derived stability conditions.

Topics & Concepts

Artificial neural networkControl theory (sociology)Stability (learning theory)Lyapunov functionInterval (graph theory)MathematicsComputer scienceLyapunov stabilityControl (management)Artificial intelligenceNonlinear systemMachine learningQuantum mechanicsCombinatoricsPhysicsNeural Networks Stability and SynchronizationStability and Control of Uncertain SystemsAdvanced Memory and Neural Computing