Passivity analysis of delayed reaction-diffusion memristor-based neural networks

Yanyi Cao; Yuting Cao; Shiping Wen; Tingwen Huang; Zhigang Zeng

doi:10.1016/j.neunet.2018.10.004

Passivity analysis of delayed reaction-diffusion memristor-based neural networks

Neural Netw. 2019 Jan:109:159-167. doi: 10.1016/j.neunet.2018.10.004. Epub 2018 Oct 29.

Authors

Yanyi Cao¹, Yuting Cao¹, Shiping Wen², Tingwen Huang³, Zhigang Zeng¹

Affiliations

¹ School of Automation, Huazhong University of Science and Technology, Wuhan, PR China.
² School of Automation, Huazhong University of Science and Technology, Wuhan, PR China. Electronic address: wenshiping226@126.com.
³ Science Program, Texas A & M University at Qatar, Doha 23874, Qatar.

PMID: 30445346
DOI: 10.1016/j.neunet.2018.10.004

Abstract

This paper discusses the passivity of delayed reaction-diffusion memristor-based neural networks (RDMNNs). By exploiting inequality techniques and by constructing appropriate Lyapunov functional, several sufficient conditions are obtained in the form of linear matrix inequalities (LMIs), which can be used to ascertain the passivity, output and input strict passivity of delayed RDMNNs. In addition, the passivity of RDMNNs without any delay is also considered. These conditions, represented by LMIs, can be easily verified by virtue of the Matlab toolbox. Finally, some illustrative examples are provided to substantiate the effectiveness and validity of the theoretical results, and to present an application of RDMNN in pseudo-random number generation.

Keywords: Memristor; Neural network; Passivity.

MeSH terms

Algorithms*
Diffusion
Neural Networks, Computer*