• DocumentCode
    3016890
  • Title

    A study of exponential stability of multiple equilibria in delayed recurrent neural networks

  • Author

    Zeng, Zhigang ; Zheng, Wei Xing

  • Author_Institution
    Dept. of Control Sci. & Eng., Huazhong Univ. of Sci. & Technol., Wuhan, China
  • fYear
    2012
  • fDate
    20-23 May 2012
  • Firstpage
    2083
  • Lastpage
    2086
  • Abstract
    The problem of exponential stability of multiple equilibria in recurrent neural networks with time-varying delays and concave-convex characteristics is addressed in this paper. The focus is placed upon derivation of some sufficient conditions under which an neural network of order n can have (2k + 2m - 1)n equilibrium points with (k + m)n of them having local exponential stability. The new results represent important extensions of the existing results on multistability of delayed recurrent neural networks.
  • Keywords
    asymptotic stability; concave programming; convex programming; delays; recurrent neural nets; time-varying systems; concave convex characteristics; delayed recurrent neural networks; equilibrium points; exponential stability; multiple equilibria; time-varying delays; Associative memory; Cellular neural networks; Delay; Recurrent neural networks; Stability analysis; Vectors;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Circuits and Systems (ISCAS), 2012 IEEE International Symposium on
  • Conference_Location
    Seoul
  • ISSN
    0271-4302
  • Print_ISBN
    978-1-4673-0218-0
  • Type

    conf

  • DOI
    10.1109/ISCAS.2012.6271693
  • Filename
    6271693
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3016890