Litcius/Paper detail

Projective Synchroniztion of Neural Networks via Continuous/Periodic Event-Based Sampling Algorithms

Shiqin Wang, Yuting Cao, Shiping Wen, Zhenyuan Guo, Tingwen Huang, Yiran Chen

2020IEEE Transactions on Network Science and Engineering29 citationsDOI

Abstract

This study concerns the projective synchronization problem of basic neural networks via continuous/periodic event-based sampling algorithms. Firstly, an event-triggering control scheme is proposed via continuous sampling. In addition, there exists a consistent positive lower bound for the time interval between two successive trigger events, which implies that the Zeno phenomenon will not occur. Next, by designing an appropriate sampling period, a more practical event-triggering scheme is proposed with periodic sampling, which can ensure the projective synchronization of the drive-response neural networks systems. Finally, several examples are elaborated to substantiate the theoretical results.

Topics & Concepts

Sampling (signal processing)Synchronization (alternating current)Computer scienceArtificial neural networkEvent (particle physics)AlgorithmInterval (graph theory)MathematicsArtificial intelligenceTopology (electrical circuits)Computer visionPhysicsCombinatoricsQuantum mechanicsFilter (signal processing)Neural Networks Stability and SynchronizationAdvanced Memory and Neural Computingstochastic dynamics and bifurcation
Projective Synchroniztion of Neural Networks via Continuous/Periodic Event-Based Sampling Algorithms | Litcius