An analysis of global exponential stability of bidirectional associative memory neural networks with constant time delays

This paper deals with the robust stability for uncertain bidirectional associative memory (BAM) neural networks of neutral-type with time-varying delays. The parameter uncertainties are assumed to be norm bounded, the discrete delays and neutral delays are time-varying delays. The combined method, which is based on the Lyapunov-Krasovskii functional (LKF) combined with some inequality techniques, is used to investigate this problem. Then, by constructing a new LKF, using the Newton-Leibniz formula and introducing some free weighting matrices, some sufficient conditions are proposed to guarantee global asymptotic robust stability for the considered systems. It is also shown that the obtained results can be established in terms of linear matrix inequality (LMI).

show abstract

“…The following result provides the feasible robust stability for systems (6) with the admissible uncertainty. …”

Section: T T D Y T R Y T H Y T H T R Y T H Tmentioning

confidence: 99%

Stability conditions for uncertain BAM neural networks of neutral-type with time-varying delays

Tang

Liu

Wang

et al. 2011

IEEE 10th International Conference on Cognitive Informatics and Cognitive Computing (ICCI-CC'11)

View full text Add to dashboard Cite

show abstract

“…Moreover, the exponential stability property is particularly important when the exponential convergence rate is used to determine the speed of neural computations. Considering this, the exponential stability analysis problem for delayed BAM neural networks has been investigated in [8,9]. Additionally, the distributed delays are unavoidable in the neural networks [10], and since then the stability analysis for neural networks with distributed delays has been investigated in [11][12][13][14].…”

Section: Introductionmentioning

confidence: 99%

Exponential convergence rate estimation for neutral BAM neural networks with mixed time-delays

Chen

Zhang

2010

Neural Comput & Applic

View full text Add to dashboard Cite

This paper is concerned with the exponential stability analysis problem for a class of neutral bidirectional associative memory neural networks with mixed timedelays, where discrete, distributed and neutral delays are involved. By utilizing the delay decomposition approach and an appropriately constructed Lyapunov-Krasovskii functional, some novel delay-dependent and decay rate-dependent criteria for the exponential stability of the considered neural networks are derived and presented in terms of linear matrix inequalities. Furthermore, the maximum allowable decay rate can be estimated based on the obtained results.Three numerical examples are given to demonstrate the effectiveness of the proposed method.

show abstract

“…As using an interval neural network having certain robustness to solve optimization problems, we need not consider spurious suboptimal responses for each parameter value of the neural network, which is of great importance. Therefore, besides global exponential stability, complete stability, asymptotic stability and periodic oscillation of neural networks with time delays have been extensively investigated by many researchers in [2][4] [5][8] [11][12] [13]. However, to best our knowledge, few authors consider the robust stability of neural networks.…”

Section: Introductionmentioning

confidence: 99%

Global Robust Stability of Neural Networks with Both Variable and Unbounded Delays

Deng

Tong

2009

2009 Fifth International Conference on Natural Computation

View full text Add to dashboard Cite

In this paper, global robust stability of neural networks with variable delays is studied. We employ homeomorphism techniques and Lyapunov functions to establish some sufficient conditions ensuring the global robust exponential stability and asymptotic stability of neural networks with variable delays. The new and useful results obtained in this paper extend and improve the existing ones in the previous literature.

show abstract

An analysis of global exponential stability of bidirectional associative memory neural networks with constant time delays

Cited by 13 publications

References 23 publications

Stability conditions for uncertain BAM neural networks of neutral-type with time-varying delays

Stability conditions for uncertain BAM neural networks of neutral-type with time-varying delays

Exponential convergence rate estimation for neutral BAM neural networks with mixed time-delays

Global Robust Stability of Neural Networks with Both Variable and Unbounded Delays

Contact Info

Product

Resources

About