Improved exponential convergence result for generalized neural networks including interval time-varying delayed signals.

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

Abstract

This article examines the exponential stability analysis problem of generalized neural networks (GNNs) including interval time-varying delayed states. A new improved exponential stability criterion is presented by establishing a proper Lyapunov-Krasovskii functional (LKF) and employing new analysis theory. The improved reciprocally convex combination (RCC) and weighted integral inequality (WII) techniques are utilized to obtain new sufficient conditions to ascertain the exponential stability result of such delayed GNNs. The superiority of the obtained results is clearly demonstrated by numerical examples.

Authors

  • G Rajchakit
    Department of Mathematics, Faculty of Science, Maejo University, Sansai 50290, Chiang Mai, Thailand.
  • R Saravanakumar
    Department of Mathematics, Faculty of Science, Maejo University, Sansai 50290, Chiang Mai, Thailand.
  • Choon Ki Ahn
  • Hamid Reza Karimi
    Department of Engineering, Faculty of Technology and Science, University of Agder, N-4898 Grimstad, Norway.