DOAJ Open Access 2021

Stability analysis for delayed neural networks based on a generalized free-weighting matrix integral inequality

ZhiZheng Zhao Wei Qian Xiaozhuo Xu

Lihat Sumber DOI

Abstrak

This paper investigates the stability problem of neural networks (NNs) with time-varying delay. Firstly, a new augmented vector and suitable Lyapunov–Krasovskii Functional (LKF) considering activation function are constructed by using more information of time delay. Secondly, a generalized free-weighting matrix integral inequality (GFMII) is chosen to estimate the derivative of single integral terms more accurately. Meanwhile, Jensen integral inequality and improved convex combination are combined to estimate integral terms with activation function; as a result, a novel stability criterion with less conservatism is established. Finally, two numerical examples are employed to illustrate the effectiveness of proposed methods.

Topik & Kata Kunci

Control engineering systems. Automatic machinery (General) Systems engineering

Penulis (3)

ZhiZheng Zhao

Wei Qian

Xiaozhuo Xu

Format Sitasi

APA MLA BibTeX

Zhao, Z., Qian, W., Xu, X. (2021). Stability analysis for delayed neural networks based on a generalized free-weighting matrix integral inequality. https://doi.org/10.1080/21642583.2020.1858363

Akses Cepat

Lihat di Sumber doi.org/10.1080/21642583.2020.1858363

Informasi Jurnal

Tahun Terbit: 2021
Sumber Database: DOAJ
DOI: 10.1080/21642583.2020.1858363
Akses: Open Access ✓