Journal of Mathematical Sciences

, Volume 187, Issue 4, pp 511–523

Global robust exponential stability for Hopfield neural networks with non-Lipschitz activation functions

Authors

  • Hongtao Yu
    • College of Information Science and EngineeringYanshan University
    • College of ScienceYanshan University
Article

DOI: 10.1007/s10958-012-1079-6

Cite this article as:
Yu, H. & Wu, H. J Math Sci (2012) 187: 511. doi:10.1007/s10958-012-1079-6

We consider the problem of global robust exponential stability for Hopfield neural networks with norm-bounded parameter uncertainties and inverse Hölder neuron activation functions. By using the Brouwer degree properties and some analysis techniques, we investigate the existence and uniqueness of an equilibrium point. Based on the Lyapunov stability theory, we derive a global robust exponential-stability criterion in terms of a linear matrix inequality (LMI). Two numerical examples are provided to demonstrate the efficiency and validity of the proposed robust stability results.

Copyright information

© Springer Science+Business Media New York 2012