LMI-based exponential stability criterion for bidirectional associative memory neural networks

Authors:
Magdi S. Mahmoud;Yuanqing Xia
Affiliations:
Systems Engineering Department, King Fahd University of Petroleum and Minerals, P. O. Box 985, Dhahran 31261, Saudi Arabia;Department of Automatic Control, Beijing Institute of Technology, Beijing 100081, China
Venue:
Neurocomputing
Year:
2010

Citing 6
Cited 4

Bidirectional associative memories

IEEE Transactions on Systems, Man and Cybernetics
Existence and stability of almost periodic solution for BAM neural networks with delays

Applied Mathematics and Computation
Stability of Time-Delay Systems

Stability of Time-Delay Systems
Global asymptotic stability of delayed bi-directional associative memory neural networks

Applied Mathematics and Computation
New delay-dependent asymptotic stability conditions concerning BAM neural networks of neutral type

Neurocomputing
Delay-independent stability in bidirectional associative memory networks

IEEE Transactions on Neural Networks

Synchronization of multiple chaotic FitzHugh-Nagumo neurons with gap junctions under external electrical stimulation

Neurocomputing
New sufficient conditions for global stability of neutral-type neural networks with time delays

Neurocomputing
Bidirectional associative memories: Different approaches

ACM Computing Surveys (CSUR)
New LMI-based conditions for global exponential stability to a class of Cohen-Grossberg BAM networks with delays

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper, we investigate the problem of global exponential stability analysis for a class of bidirectional associative memory (BAM) neural networks with interval time-delays. Improved exponential stability condition is derived by employing new Lyapunov-Krasovskii functional and the integral inequality. Several special cases of interest are derived. The developed stability criteria are delay dependent and characterized by linear matrix inequalities (LMIs). The developed results are shown to be less conservative than previous published ones in the literature. Finally, simulations of two numerical examples are provided to demonstrate the efficacy of our approach.