On stability of multiple equilibria for delayed neural networks with discontinuous activation functions

Xiaobing Nie, Wei Xing Zheng

    Research output: Chapter in Book / Conference PaperConference Paperpeer-review

    2 Citations (Scopus)

    Abstract

    This paper considers the stability problem of multiple equilibria for delayed neural networks with discontinuous activation functions. By virtue of the fixed point theorem, it is found that under some sufficient conditions, n neurons delayed neural networks with discontinuous non-monotonic activation functions can have at least 4â„¢ equilibrium points and 3â„¢ of them are locally stable. Furthermore, it is shown that the storage capacity of the neural networks can be considerably expanded by use of discontinuous activation functions, which is important in several neural network applications. Finally, the effectiveness of the theoretical findings is verified by a numerical example.
    Original languageEnglish
    Title of host publicationProceedings of 34th Chinese Control Conference (CCC2015), July 28-30, 2015, Hangzhou, China
    PublisherIEEE
    Pages3542-3547
    Number of pages6
    ISBN (Print)9781467374439
    DOIs
    Publication statusPublished - 2015
    EventChinese Control Conference -
    Duration: 28 Jul 2015 → …

    Publication series

    Name
    ISSN (Print)1934-1768

    Conference

    ConferenceChinese Control Conference
    Period28/07/15 → …

    Keywords

    • multistability
    • neural networks (computer science)
    • time delay systems

    Fingerprint

    Dive into the research topics of 'On stability of multiple equilibria for delayed neural networks with discontinuous activation functions'. Together they form a unique fingerprint.

    Cite this