A Novel Condition for Robust Stability of Delayed Neural Networks


Ozcan N., YÜCEL DEMİREL E., Arik S.

22nd International Conference on Neural Information Processing (ICONIP), İstanbul, Türkiye, 9 - 12 Kasım 2015, cilt.9491, ss.273-280 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 9491
  • Doi Numarası: 10.1007/978-3-319-26555-1_31
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.273-280
  • Bursa Uludağ Üniversitesi Adresli: Evet

Özet

This paper presents a novel sufficient condition for the existence, uniqueness and global robust asymptotic stability of the equilibrium point for the class of delayed neural networks by using the Homomorphic mapping and the Lyapunov stability theorems. An important feature of the obtained result is its low computational complexity as the reported result can be verified by checking some well-known properties of some certain classes of matrices, which simplify the verification of the derived result.