A novel condition for robust stability of delayed neural networks
Date
2015
Authors
Yücel, Eylem
Arık, Sabri
Journal Title
Journal ISSN
Volume Title
Publisher
Springer
Abstract
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.
Description
Bu çalışma, 9-12 Kasım 2015 tarihleri arasında İstanbul[Türkiye]'da düzenlenen 22. International Conference on Neural Information Processing (ICONIP)'de bildiri olarak sunulmuştur.
Keywords
Computer science, Lyapunov functional, Neural networks, Stability analysis, Asymptotic stability, Information science, Lyapunov functions, Robustness (control systems), Stability, Delayed neural networks, Equilibrium point, Global robust asymptotic stabilities, Important features, Low computational complexity, Lyapunov functionals, Lyapunov stability theorem, Complex networks
Citation
Neyir, Ö. vd. (2015). "A novel condition for robust stability of delayed neural networks". Neural Information Processing, PT III, Lecture Notes in Computer Science, 273-280.