Finite-Time Nonchattering Synchronization of Coupled Neural Networks With Multi-Weights

• Published in: IEEE transactions on network science and engineering Vol. 10; no. 4; pp. 1 - 14
• Main Authors: Zhao, Lin-Hao, Wen, Shiping, Guo, Zhenyuan, Shi, Kaibo, Xiao, Jianying, Zhu, Song, Huang, Tingwen
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.07.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Convolutional neural networks; Coupled neural networks; Couplings; finite-time <inline-formula xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"> <tex-math notation="LaTeX"> mathcal {H}_{\infty }</tex-math> </inline-formula> synchronization; finite-time synchronization; multiple derivative couplings; Neural networks; Neurons; nonchattering control; Sociology; Stochastic processes; Switches; Synchronization; Time synchronization
• ISSN: 2327-4697; 2334-329X
• DOI: 10.1109/TNSE.2023.3243610

This paper is concerned with finite-time synchronization and finite-time <inline-formula><tex-math notation="LaTeX">\mathcal {H}_{\infty }</tex-math></inline-formula> synchronization for coupled neural networks with multiple state/derivative couplings. Firstly, several sufficient conditions are developed to guarantee the finite-time synchronization for these two networks by using some inequality techniques. Secondly, based on the Lyapunov functional, finite-time <inline-formula><tex-math notation="LaTeX">\mathcal {H}_{\infty }</tex-math></inline-formula> synchronization problems for those two networks are respectively tackled. Thirdly, nonchattering controllers are designed to overcome the chattering phenomenon appearing in a finite-time controller with the sign function. Finally, two numerical examples are provided to illustrate the effectiveness and correctness of our results.