Improved Stability Criteria for Delayed Neural Networks Using a Quadratic Function Negative-Definiteness Approach.

Journal: IEEE transactions on neural networks and learning systems
Published Date:

Abstract

This brief is concerned with the stability of a neural network with a time-varying delay using the quadratic function negative-definiteness approach reported recently. A more general reciprocally convex combination inequality is taken to introduce some quadratic terms into the time derivative of a Lyapunov-Krasovskii (L-K) functional. As a result, the time derivative of the L-K functional is estimated by a novel quadratic function on the time-varying delay. Moreover, a simple way is introduced to calculate the coefficients of a quadratic function, which avoids tedious works by hand as done in some studies. The L-K functional approach is applied to derive a hierarchical type stability criterion for the delayed neural networks, which is of less conservatism in comparison with some existing results through two well-studied numerical examples.

Authors

  • Jun Chen
    Department of Bioengineering, University of California, Los Angeles, Los Angeles, CA 90095, USA.
  • Xian-Ming Zhang
  • Ju H Park
    Department of Electrical Engineering, Yeungnam University, 280 Daehak-Ro, Kyongsan 38541, Republic of Korea. Electronic address: jessie@ynu.ac.kr.
  • Shengyuan Xu