Robust stability analysis of quaternion-valued neural networks with time delays and parameter uncertainties.

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

Abstract

This paper addresses the problem of robust stability for quaternion-valued neural networks (QVNNs) with leakage delay, discrete delay and parameter uncertainties. Based on Homeomorphic mapping theorem and Lyapunov theorem, via modulus inequality technique of quaternions, some sufficient conditions on the existence, uniqueness, and global robust stability of the equilibrium point are derived for the delayed QVNNs with parameter uncertainties. Furthermore, as direct applications of these results, several sufficient conditions are obtained for checking the global robust stability of QVNNs without leakage delay as well as complex-valued neural networks (CVNNs) with both leakage and discrete delays. Finally, two numerical examples are provided to substantiate the effectiveness of the proposed results.

Authors

  • Xiaofeng Chen
    Department of Mathematics, Chongqing Jiaotong University, Chongqing, 400074, China; Department of Mathematics and Statistics, Georgia State University, Atlanta, GA 30302, USA. Electronic address: xxffch@126.com.
  • Zhongshan Li
    Department of Mathematics and Statistics, Georgia State University, Atlanta, GA 30302, USA. Electronic address: zli@gsu.edu.
  • Qiankun Song
    Department of Mathematics, Chongqing Jiaotong University, Chongqing 400074, China. Electronic address: qiankunsong@163.com.
  • Jin Hu
    Department of Mathematics, Chongqing Jiaotong University, Chongqing, China. Electronic address: windyvictor@gmail.com.
  • Yuanshun Tan
    Department of Mathematics, Chongqing Jiaotong University, Chongqing, 400074, China. Electronic address: tanys@cqjtu.edu.cn.