Stability analysis of multiple equilibria for recurrent neural networks with discontinuous Mexican-hat-type activation function

Xiaobing Nie, Wei Xing Zheng, Jinhu Lü

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

    Abstract

    ![CDATA[This paper is concerned with stability analysis of multiple equilibria for recurrent neural networks. A new type of activation function, namely, discontinuous Mexican-hat-type activation function, is proposed for recurrent neural networks. Then with the aid of the fixed point theorem, some sufficient conditions for coexistent multiple equilibria are obtained to guarantee that such n-neuron recurrent neural networks can have at least 4n equilibria. In view of the theory of strict diagonal dominance matrix, further stability analysis reveals that 3n equilibria are locally exponentially stable. The new results considerably improve the existing multistability results in the literature.]]
    Original languageEnglish
    Title of host publicationProceedings: 2015 IEEE International Symposium on Circuits and Systems, ISCAS 2015, Lisbon, Portugal, 24-27 May 2015
    PublisherIEEE
    Pages569-572
    Number of pages4
    ISBN (Print)9781479983926
    DOIs
    Publication statusPublished - 2015
    EventIEEE International Symposium on Circuits and Systems -
    Duration: 24 May 2015 → …

    Publication series

    Name
    ISSN (Print)0271-4310

    Conference

    ConferenceIEEE International Symposium on Circuits and Systems
    Period24/05/15 → …

    Keywords

    • fixed point theory
    • matrices
    • recurrent neural networks
    • stability analysis

    Fingerprint

    Dive into the research topics of 'Stability analysis of multiple equilibria for recurrent neural networks with discontinuous Mexican-hat-type activation function'. Together they form a unique fingerprint.

    Cite this