Acta mathematica scientia,Series A ›› 2019, Vol. 39 ›› Issue (5): 1192-1204.

Previous Articles    

Global Exponential Periodicity of Complex-Valued Neural Networks with Discontinuous Activation Functions

Zou Yao1, Zeng Chunna2, Hu Jin1   

  1. 1 School of Mathematics and Statistics, Chongqing Jiaotong University, Chongqing 400074;
    2 School of Mathematical Sciences, Chongqing Normal University, Chongqing 401331
  • Received:2018-10-31 Revised:2018-11-25 Published:2019-11-08
  • Supported by:
    Supported by the NSFC (61773004, 11801048), the Program of Chongqing Innovation Team Project in University (CXTDX201601022), the Natural Scinece Foundation Project of CQ CSTC (cstc2017jcyjAX0172, cstc2017jcyjAX0022, cstc2017jcyjAX0082, cstc2018jcyjAX0606), the Technology Research Foundation of Chongqing Educational Committee (KJ1705118, KJQN201800740) and the Venture & Innovation Support Program for Chongqing Overseas Returnees (cx2018034)

Abstract: In this paper, we investigate a type of complex-valued neural networks with discontinuous activation functions. By using Filippov differential inclusion theory, Leray-Schauder alternative theorem and Lyapunov function, we obtain the sufficiet conditions for the global exponential periodicity of the neural network. The simulation shows the effectiveness of the results.

Key words: Complex-valued neural networks, Discontinuous activation functions, Global exponential periodicity

CLC Number: 

  • O175.13