Advanced Search

Query:

Fill in the form and click »Search«...

Format:

Display: entries per page entries

Zbl 1160.92002
Huang, Lihong; Wang, Jiafu; Zhou, Xiangnan
Existence and global asymptotic stability of periodic solutions for Hopfield neural networks with discontinuous activations. (English)
[J] Nonlinear Anal., Real World Appl. 10, No. 3, 1651-1661 (2009). ISSN 1468-1218

Summary: We study a class of neural networks with discontinuous activations, which include bidirectional associative memory networks and cellular networks as its special cases. By the Leray-Schauder alternative theorem, matrix theory and a generalized Lyapunov approach, we obtain some sufficient conditions ensuring the existence, uniqueness and global asymptotic stability of periodic solutions. Our results are less restrictive than previously known criteria and can be applied to neural networks with a broad range of activation functions assuming neither boundedness nor monotonicity.

MSC 2000:: *92B20 General theory of neural networks
68T05 Learning and adaptive systems
34C25 Periodic solutions of ODE
34D23 Global stability

Keywords: discontinuous dynamical system; periodic solution; global asymptotic stability; Leray-Schauder alternative theorem

Comment on this Item PDF MathML XML ASCII DVI PS BibTeX Online Ordering Article Journal

	Scientific prize winners of the ICM 2010
	Overhang
	Lie groups, physics and geometry. An introduction for physicists, engineers and chemists.

Advanced Search

Zentralblatt MATH Berlin [Germany]