Multistability of switched neural networks with sigmoidal activation functions under state-dependent switching.

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

Abstract

This paper presents theoretical results on the multistability of switched neural networks with commonly used sigmoidal activation functions under state-dependent switching. The multistability analysis with such an activation function is difficult because state-space partition is not as straightforward as that with piecewise-linear activations. Sufficient conditions are derived for ascertaining the existence and stability of multiple equilibria. It is shown that the number of stable equilibria of an n-neuron switched neural networks is up to 3 under given conditions. In contrast to existing multistability results with piecewise-linear activation functions, the results herein are also applicable to the equilibria at switching points. Four examples are discussed to substantiate the theoretical results.

Authors

  • Zhenyuan Guo
    College of Mathematics and Econometrics, Hunan University, Changsha, Hunan 410082, PR China; Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong. Electronic address: zyguo@hnu.edu.cn.
  • Shiqin Ou
    College of Mathematics and Econometrics, Hunan University, Changsha, Hunan 410082, China.
  • Jun Wang
    Department of Speech, Language, and Hearing Sciences and the Department of Neurology, The University of Texas at Austin, Austin, TX 78712, USA.