Almost Periodic Solutions of Recurrent Neural Networks with State-Dependent and Structured Impulses

AKHMET M., ERİM G.

Discontinuity, Nonlinearity, and Complexity, cilt.12, sa.1, ss.141-165, 2023 (Scopus) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 12 Sayı: 1
  • Basım Tarihi: 2023
  • Doi Numarası: 10.5890/dnc.2023.03.011
  • Dergi Adı: Discontinuity, Nonlinearity, and Complexity
  • Derginin Tarandığı İndeksler: Scopus
  • Sayfa Sayıları: ss.141-165
  • Anahtar Kelimeler: Asymptotic stability, B-equivalence method, Discontinuous almost periodic motions, Neural networks with negative/, Positive capacitance, Recurrent impulsive neural networks, Recurrently structured impacts
  • Orta Doğu Teknik Üniversitesi Adresli: Evet

Özet

© 2023 L&H Scientific Publishing, LLC. All rights reserved.The subject of the present paper is recurrent neural networks with variable impulsive moments. The impact activation functions are specified such that the structure for the jump equations are in full accordance with that one for the differential equation. The system studied in this paper covers the works done before, not only because the impacts have recurrent form, but also impulses are not state-dependent. The conditions for existence and uniqueness of asymptotically stable discontinuous almost periodic solutions are obtained. Through the present study, the possibility of neuron membranes with negative capacitance is involved in neural networks and this is one of the main novelties of the present study. The vector-matrix representation of the system is used for the clarity of the proofs and for making calculations easier.