Delayed neural networks with periodic coefficients and discontinuous and/or unbounded activation functions are investigated by means of Lyapunov theory and fixed point theorems. We obtain conditions, independent from the delay, assuring the existence of an unique limit cycle, which is globally exponential stable.
Global exponential stability of the periodic solution of a delayed neural network with discontinuous activations / Papini, D; Taddei, Valentina. - In: PHYSICS LETTERS A. - ISSN 0375-9601. - STAMPA. - 343:1-3(2005), pp. 117-128. [10.1016/j.physleta.2005.06.015]
Global exponential stability of the periodic solution of a delayed neural network with discontinuous activations
PAPINI D;TADDEI, Valentina
2005
Abstract
Delayed neural networks with periodic coefficients and discontinuous and/or unbounded activation functions are investigated by means of Lyapunov theory and fixed point theorems. We obtain conditions, independent from the delay, assuring the existence of an unique limit cycle, which is globally exponential stable.
| File | Dimensione | Formato | |
|---|---|---|---|
|
Papini-Taddei1.pdf
Accesso riservato
Tipologia:
Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione
148.77 kB
Formato
Adobe PDF
|
148.77 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris
