Solutions For BAM Neural Networks Research Articles

Influence of Leakage Delay on Almost Periodic Solutions for BAM Neural Networks

In this paper, we deal with a class of BAM neural networks with time-varying leakage delays. By applying the exponential dichotomy of linear differential equations, fixed point theorems and differential inequality techniques, we obtain some sufficient conditions which guarantee the existence and exponential stability of almost periodic solutions for such class of BAM neural networks. An example is provided to illustrate the effectiveness of the theoretical predictions. The results obtained in this paper are completely new and complement the previously known publications.

Exponential Stability of Antiperiodic Solution for BAM Neural Networks with Time-Varying Delays

In this paper, a kind of BAM neural networks with leakage delays in the negative feedback terms and time-varying delays in activation functions was considered. By constructing a suitable Lyapunov function and using inequality techniques, some sufficient conditions to ensure the existence and exponential stability of antiperiodic solutions of these neural networks were derived. These conditions extend some results recently appearing in recent papers. Lastly, an example is given to show the feasibility of these conditions.

Existence and global exponential stability of anti-periodic solutions for BAM neural networks with inertial term and delay

This paper is concerned with the existence and exponential stability of anti-periodic solutions of BAM neural networks with inertial term and delay. Applying inequality techniques and Lyapunov method, sufficient conditions which ensure the existence and exponential stability of anti-periodic solutions of BAM neural networks are presented. Our results are new and supplement some previously known ones.

Periodic Solutions of BAM Neural Networks with Continuously Distributed Delays in the Leakage Terms

This paper concerns with bidirectional associative memory neural network model with continuously distributed leakage delays. By applying Lyapunov functional method and differential inequality techniques, we establish some sufficient conditions for the existence and exponential stability of periodic solutions for the model, which complement with some recent ones. Moreover, an example and its numerical simulation are given to support the theoretical results.

Existence and Exponential Stability of Almost Periodic Solution for BAM Neural Networks on Time Scales

This paper is concerned with a class of BAM neural networks with variable coefficients on almost periodic time scales. Some sufficient conditions are established for the existence and global exponential stability of the almost periodic solution. These results have important leading significance in designs and applications of BAM neural networks. Finally, examples are presented to illustrate the feasibility and effectiveness of the results.

Anti-periodic solutions for BAM neural networks with time delays

In the paper, bidirectional associative memory neural networks with time delays are studied. By using the fundamental solution matrix of coefficients and Lyapunow function, sufficient conditions are obtained for the existence and global exponential stability of the anti-periodic solution of the model. An example and numerical simulations are also given to illustrate the theoretical results.

BAM-type impulsive neural networks with time-varying delays

By using the continuation theorem of coincidence degree theory and constructing a suitable Lyapunov functional, we derive some sufficient conditions for the existence and global exponential stability of a unique periodic solution of BAM neural networks, which assumes neither the monotony nor the boundedness of the activation functions. It is believed that these results are significant and useful for the design and applications of BAM neural networks.

Stability analysis for periodic solution of BAM neural networks with discontinuous neuron activations and impulses

In this paper, we present a general class of BAM neural networks with discontinuous neuron activations and impulses. By using the fixed point theorem in differential inclusions theory, we investigate the existence of periodic solution for this neural network. By constructing the suitable Lyapunov function, we give a sufficient condition which ensures the uniqueness and global exponential stability of the periodic solution. The results of this paper show that the Forti’s conjecture is true for BAM neural networks with discontinuous neuron activations and impulses. Further, a numerical example is given to demonstrate the effectiveness of the results obtained in this paper.

Existence and stability of periodic solution for BAM neural networks with discontinuous neuron activations

In this paper, by using the fixed point theorem of differential inclusion theory and constructing suitable Lyapunov functions, the existence, uniqueness and global exponential stability of the periodic solution for BAM neural networks with discontinuous neuron activations are investigated. Moreover, the global convergence in finite time of the networks is discussed. The conditions that ensure the existence and stability of periodic solution are given. The obtained results extend previous work on global stability of BAM neural networks with Lipschitz continuous neuron activations but without delays, and show that Forti’s conjecture is true for BAM neural networks without delays.

Existence and exponential stability of almost periodic solution for BAM neural networks with variable coefficients and delays

By using exponential dichotomy, the Banach fixed point theory, constructing suitable Lyapunov functional, and combining Yang inequality, some sufficient conditions are derived ensuring existence, globally exponential stability of almost periodic solution for BAM neural networks with variable coefficients and delays. Without assuming the boundedness of signal function, these results obtained are significant in design and applications of BAM neural networks. We extend and improve previously known results.

An analysis on existence and global exponential stability of periodic solutions for BAM neural networks with time-varying delays

In this paper, the problem on periodic solutions of the bidirectional associative memory neural networks with both periodic coefficients and periodic time-varying delays is discussed. By using analytic methods, inequality technique and M-matrix theory, several sufficient conditions ensuring the existence, uniqueness, and global exponential stability of periodic solution are derived. Moreover, the exponential convergence rate index is estimated, which depends on the system parameters. Some existing results are improved and extended. The obtained results are less restrictive than previously known criteria, and the hypothesis for the boundedness and monotonicity on the activation functions and the differentiability on the time-varying delays are removed. An example is given to show the effectiveness of the obtained results.

Existence and exponential stability of periodic solution of BAM neural networks with impulse and time-varying delay

This paper investigates the global periodicity of BAM neural network with impulses and time-delay. Several conditions guaranteeing the existence, uniqueness, and global exponential stability of periodic solution are obtained. A numerical example is given to illustrate the effectiveness of our results.

New results on the existence and uniqueness of almost periodic solution for BAM neural networks with continuously distributed delays

Abstract In this paper, a class of BAM neural networks with continuously distributed delays are studied. Some new sufficient conditions are established for the existence and uniqueness of the almost periodic solution, which generalize and improve the previously known results. Moreover, the method used in the proof is original. An example is presented to illustrate the feasibility and effectiveness of the new results.

Existence and stability of periodic solution for BAM neural networks with distributed delays

We use the continuation theorem of coincidence degree theory and Liapunov functions to study the existence and stability of positive periodic solutions for a class of two-layer heteroassociative networks called bidirectional associative memory networks dx i dt =−a i(t)x i(t)+∑ j=1 mp ji(t)f j(y j(t−τ ji(t,y j(t))))+I i(t), i=1,2,…,n, dy j dt =−b j(t)y j(t)+∑ i=1 nq ij(t)f i(x i(t−σ ij(t,x i(t))))+J j(t), j=1,2,…,m and dx i dt =−a i(t)x i(t)+∑ j=1 mp ji(t)f j ∫ 0 ∞h ji(s)y j(t−s) ds +I i(t), i=1,2,…,n, dy j dt =−b j(t)y j(t)+∑ i=1 nq ij(t)f i ∫ 0 ∞k ij(s)x i(t−s) ds +J j(t), j=1,2,…,m.

Existence and global exponential stability of almost periodic solutions of BAM neural networks with continuously distributed delays

Several sufficient conditions are obtained ensuring the existence and global exponential stability of almost periodic solution for BAM neural networks with distributed delays based on fixed point method and some analysis technique. Some previous results are improved and extended in this Letter and an example is given to illustrate the conditions of our results are feasible. These results are helpful to design globally exponentially stable BAM networks with continuously distributed delays.

Existence and global exponential stability of periodic solution for bam neural networks with periodic coefficients and time-varying delays

Several sufficient conditions are obtained ensuring existence and global exponential stability of periodic solution for the bidirectional associative memory (BAM) neural networks with periodic coefficients and time-varying delays by using the continuation theorem of Mawhin's coincidence degree theory and Gronwall's inequality. These results are helpful to design globally exponentially stable BAM networks and periodic oscillatory neural networks.

Existence and stability of almost periodic solution for BAM neural networks with delays

By using the Banach fixed point theorem and constructing suitable Lyapunov function, some sufficient conditions are obtained ensuring existence, uniqueness and global stability of almost periodic solution of the BAM neural networks with variable coefficients and delays. These results are helpful to design global exponential stable BAM networks and almost periodic oscillatory BAM networks.