Global stability of a larger class of dynamical neural networks

Arik S.

IEEE International Symposium on Circuits and Systems (ISCAS 98), Monterrey, Meksika, 31 Mayıs - 03 Haziran 1998, (Tam Metin Bildiri) identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası:
  • Basıldığı Şehir: Monterrey
  • Basıldığı Ülke: Meksika
  • İstanbul Üniversitesi-Cerrahpaşa Adresli: Evet

Özet

In this paper, we present a sufficient condition for the existence, uniqueness and global asymptotic stability (GAS) of the equilibrium point for a larger class of dynamical neural networks. It is shown that the digonal dominance of the interconnection matrix guarantees the existence, uniqueness and GAS of the equilibrium point with respect to all nondecreasing activation functions.