Input-to-state stability of delayed memristor-based inertial neural networks via non-reduced order method.

Journal: Neural networks : the official journal of the International Neural Network Society
Published Date:

Abstract

This paper is concerned with the input-to-state stability (ISS) for a kind of delayed memristor-based inertial neural networks (DMINNs). Based on the nonsmooth analysis and stability theory, novel delay-dependent and delay-independent criteria on the ISS of DMINNs are obtained by constructing different Lyapunov functions. Moreover, compared with the reduced order approach used in the previous works, this paper consider the ISS of DMINNs via non-reduced order approach. Directly analysis the model of DMINNs can better maintain its physical backgrounds, which reduces the complexity of calculations and is more rigorous in practical application. Additionally, the novel proposed results on the ISS of DMINNs here incorporate and complement the existing studies on memristive neural network dynamical systems. Lastly, a numerical example is provided to show that the obtained criteria are reliable.

Authors

  • Yuxin Jiang
    Department of Ultrasound, Chinese Academy of Medical Sciences and Peking Union Medical College Hospital, Beijing, China.
  • Song Zhu
    College of Sciences, China University of Mining and Technology, Xuzhou, 221116, China. Electronic address: songzhu82@gmail.com.
  • Xiaoyang Liu
    School of Computer Science & Technology, Jiangsu Normal University, Xuzhou 221116, China. Electronic address: liuxiaoyang1979@gmail.com.
  • Shiping Wen
  • Chaoxu Mu