A systematic method for complete stability problem of a class of delayed neural networks in parameter space

This paper presents a systematic method to address the complete stability problem of delayed neural networks with heterogeneous free parameters. First, we adopt an algebraic method to investigate the complete stability problem with respect to the free delay parameter τ. Then, the stability analysis...

Teljes leírás

Elmentve itt :
Bibliográfiai részletek
Szerzők: Chen Jun-Xiu
Li Xu
Dokumentumtípus: Folyóirat
Megjelent: 2025
Sorozat:Electronic journal of qualitative theory of differential equations
Kulcsszavak:Neurális hálózatok, Differenciálegyenlet - késleltetett
Tárgyszavak:
doi:10.14232/ejqtde.2025.1.52

Online Access:http://acta.bibl.u-szeged.hu/88932
Leíró adatok
Tartalmi kivonat:This paper presents a systematic method to address the complete stability problem of delayed neural networks with heterogeneous free parameters. First, we adopt an algebraic method to investigate the complete stability problem with respect to the free delay parameter τ. Then, the stability analysis is extended to the scenario with additional free system parameters, denoted by a vector X. We can investigate the complete root classification for the auxiliary characteristic equation in the entire (X, τ)- space. As a result, we can analytically calculate the number of stability τ-intervals and characterize all classifications of stability property over the whole (X, τ)-space. Finally, we will give a systematic method for determining the stability set in the whole (X, τ)- space. Some representative examples show the effectiveness of the approach.
Terjedelem/Fizikai jellemzők:24
ISSN:1417-3875