• DocumentCode
    1333419
  • Title

    A proof of Kaszkurewicz and Bhaya´s conjecture on absolute stability of neural networks in two-neuron case

  • Author

    Liang, Xue-Bin ; Wang, Jun

  • Author_Institution
    Dept. of Electr. Eng., Arizona State Univ., Tempe, AZ, USA
  • Volume
    47
  • Issue
    4
  • fYear
    2000
  • fDate
    4/1/2000 12:00:00 AM
  • Firstpage
    609
  • Lastpage
    611
  • Abstract
    This letter presents a proof of Kaszkurewicz and Bhaya´s conjecture (1995) on the absolute stability of neural networks in the two-neuron case. The conjecture states that the necessary and sufficient condition for absolute stability of neural networks with an n×n interconnection matrix T is T∈I0, where I0 denotes the class of matrices T such that matrix (T-D1)D2 has all eigenvalues with negative real parts for arbitrary positive diagonal matrices D1 and D2 . A characterization condition for the I0 class of matrices in the two-dimensional (2-D) case n=2 is also obtained
  • Keywords
    absolute stability; neural nets; absolute stability; eigenvalues; interconnection matrix; neural network; two-dimensional system; two-neuron system; Automatic control; Circuit stability; Control systems; Convergence; Delay systems; History; Intelligent networks; Neural networks; Robust control; Robust stability;
  • fLanguage
    English
  • Journal_Title
    Circuits and Systems I: Fundamental Theory and Applications, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    1057-7122
  • Type

    jour

  • DOI
    10.1109/81.841868
  • Filename
    841868