Convergence for HRNNs with Unbounded Activation Functions and Time-varying Delays in the Leakage Terms

  • Authors:
  • Renwei Jia;Mingquan Yang

  • Affiliations:
  • College of Mathematics and Computer Science, Hunan University of Arts and Science, Changde, People's Republic of China 415000;Nanhu College, Jiaxing University, Jiaxing, People's Republic of China 314001

  • Venue:
  • Neural Processing Letters
  • Year:
  • 2014

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, the exponential convergence problems are considered for a class of high-order recurrent neural networks (HRNNs) with time-varying delays in the leakage terms. Without assuming the boundedness on the activation functions, some sufficient conditions are derived to ensure that all solutions of this system converge exponentially to zero point by using Lyapunov functional method and differential inequality techniques. It is believed that these results are significant and useful for the design and applications of HRNNs. Even for the system without leakage delays, the criterion is shown to be different from a recent publication. Moreover, some examples are given to show the effectiveness of the proposed method and results.