On exponential stability of bidirectional associative memory neural networks with time-varying delays

2009 ◽  
Vol 39 (3) ◽  
pp. 1083-1091 ◽  
Author(s):  
Ju H. Park ◽  
S.M. Lee ◽  
O.M. Kwon
Keyword(s):  
Neural Networks ◽  
Exponential Stability ◽  
Associative Memory ◽  
Time Varying ◽  
Bidirectional Associative Memory

Global exponential stability analysis of anti-periodic solutions of discontinuous bidirectional associative memory (BAM) neural networks with time-varying delays

2020 ◽  
Vol 21 (7-8) ◽  
pp. 807-820
Author(s):  
Xiangying Fu ◽  
Fanchao Kong
Keyword(s):  
Neural Networks ◽  
Exponential Stability ◽  
Periodic Solutions ◽  
Associative Memory ◽  
Time Varying ◽  
Bam Neural Networks ◽  
Bidirectional Associative Memory ◽  
Globally Exponential Stability ◽  
Discontinuous Activations ◽  
Neural Network System

AbstractThis paper is concerned with a class of bidirectional associative memory (BAM) neural networks with discontinuous activations and time-varying delays. Under the basic framework of differential inclusions theory, the existence result of solutions in sense of Filippov solution is firstly established by using the fundamental solution matrix of coefficients and inequality analysis technique. Also, the boundness of the solutions can be estimated. Secondly, based on the non-smooth Lyapunov-like approach and by construsting suitable Lyapunov–Krasovskii functionals, some new sufficient criteria are given to ascertain the globally exponential stability of the anti-periodic solutions for the proposed neural network system. Furthermore, we have collated our effort with some previous existing ones in the literatures and showed that it can take more advantages. Finally, two examples with numerical simulations are exploited to illustrate the correctness.

scholarly journals Global Exponential Stability Criteria for Bidirectional Associative Memory Neural Networks with Time-Varying Delays

2013 ◽  
Vol 2013 ◽  
pp. 1-13 ◽  
Author(s):  
J. Thipcha ◽  
P. Niamsup
Keyword(s):  
Neural Networks ◽  
Exponential Stability ◽  
Associative Memory ◽  
Global Exponential Stability ◽  
Linear Matrix ◽  
Time Varying ◽  
Stability Criteria ◽  
Bidirectional Associative Memory ◽  
Lower And Upper Bounds ◽  
Delay Dependent

The global exponential stability for bidirectional associative memory neural networks with time-varying delays is studied. In our study, the lower and upper bounds of the activation functions are allowed to be either positive, negative, or zero. By constructing new and improved Lyapunov-Krasovskii functional and introducing free-weighting matrices, a new and improved delay-dependent exponential stability for BAM neural networks with time-varying delays is derived in the form of linear matrix inequality (LMI). Numerical examples are given to demonstrate that the derived condition is less conservative than some existing results given in the literature.

scholarly journals Robust Stability Analysis of Neutral-Type Hybrid Bidirectional Associative Memory Neural Networks with Time-Varying Delays

2014 ◽  
Vol 2014 ◽  
pp. 1-12
Author(s):  
Wei Feng ◽  
Simon X. Yang ◽  
Haixia Wu
Keyword(s):  
Neural Networks ◽  
Stability Analysis ◽  
Associative Memory ◽  
Robust Stability ◽  
Neutral Type ◽  
Time Varying ◽  
Bidirectional Associative Memory ◽  
Numerical Examples ◽  
Network Parameters ◽  
Robust Stability Analysis

The global asymptotic robust stability of equilibrium is considered for neutral-type hybrid bidirectional associative memory neural networks with time-varying delays and parameters uncertainties. The results we obtained in this paper are delay-derivative-dependent and establish various relationships between the network parameters only. Therefore, the results of this paper are applicable to a larger class of neural networks and can be easily verified when compared with the previously reported literature results. Two numerical examples are illustrated to verify our results.

Sign in / Sign up

Export Citation Format

Share Document