Global Exponential Stability of Recurrent Neural Networks with Time-Dependent Switching Dynamics Conference Paper uri icon

abstract

  • In this paper, the switching dynamics of recurrent neural networks are studied. Sufficient conditions on global exponential stability with an arbitrary switching law or a dwell time switching law and the estimates of Lyapunov exponent are obtained. The obtained results can be used to analyze and synthesize a family of continuous-time configurations with the switching between the configurations. Specially, the obtained results are new and efficacious for the switching between the stable and unstable configurations. Finally, simulation results are discussed to illustrate the theoretical results. 2009 Springer Berlin Heidelberg.

published proceedings

  • ARTIFICIAL NEURAL NETWORKS - ICANN 2009, PT II

author list (cited authors)

  • Zeng, Z., Wang, J., & Huang, T.

citation count

  • 0

complete list of authors

  • Zeng, Zhigang||Wang, Jun||Huang, Tingwen

publication date

  • November 2009