Litcius/Paper detail

Fixed-Time Synchronization of Coupled Neural Networks With Discontinuous Activation and Mismatched Parameters

Na Li, Xiaoqun Wu, Jianwen Feng, Yuhua Xu, Jinhu Lü

2020IEEE Transactions on Neural Networks and Learning Systems121 citationsDOI

Abstract

This article is concerned with fixed-time synchronization of the nonlinearly coupled neural networks with discontinuous activation and mismatched parameters. First, a novel lemma is proposed to study fixed-time stability, which is less conservative than those in most existing results. Then, based on the new lemma, a discontinuous neural network with mismatched parameters will synchronize to the target state within a settling time via two kinds of unified and simple controllers. The settling time is theoretically estimated, which is independent of the initial values of the considered network. In particular, the estimated settling time is closer to the real synchronization time than those given in the existing literature. Finally, two numerical simulations are presented to illustrate the effectiveness and correctness of our results.

Topics & Concepts

Settling timeLemma (botany)Synchronization (alternating current)Control theory (sociology)CorrectnessArtificial neural networkComputer scienceSimple (philosophy)Stability (learning theory)MathematicsTopology (electrical circuits)AlgorithmArtificial intelligenceControl engineeringControl (management)EngineeringStep responsePhilosophyEpistemologyPoaceaeBiologyMachine learningCombinatoricsEcologyNeural Networks Stability and SynchronizationNonlinear Dynamics and Pattern FormationAdvanced Memory and Neural Computing