Stability Of Quaternion-valued Neural Networks Research Articles

Local Lagrange Exponential Stability Analysis of Quaternion-Valued Neural Networks with Time Delays

This study on the local stability of quaternion-valued neural networks is of great significance to the application of associative memory and pattern recognition. In the research, we study local Lagrange exponential stability of quaternion-valued neural networks with time delays. By separating the quaternion-valued neural networks into a real part and three imaginary parts, separating the quaternion field into 34n subregions, and using the intermediate value theorem, sufficient conditions are proposed to ensure quaternion-valued neural networks have 34n equilibrium points. According to the Halanay inequality, the conditions for the existence of 24n local Lagrange exponentially stable equilibria of quaternion-valued neural networks are established. The obtained stability results improve and extend the existing ones. Under the same conditions, quaternion-valued neural networks have more stable equilibrium points than complex-valued neural networks and real-valued neural networks. The validity of the theoretical results were verified by an example.

Further research on exponential stability for quaternion-valued neural networks with mixed delays

This paper addresses the global exponential stability of a class of quaternion-valued neural networks (QVNNs) with mixed delays including time-varying delays and infinite distributed delays. Because of the noncommutativity of quaternion multiplication, the concerned quaternion-valued models separated into four real-valued parts to form the equivalent real-valued systems. Based on M-matrix properties and homomorphism mapping theories, some sufficient conditions are derived to guarantee the existence and uniqueness of the equilibrium point of the system. Conditions for ensuring the global exponential stability of the equilibrium point of the system are obtained on the basis of the vector Lyapunov function method instead of the linear matrix inequality method. Using a similar method, the mixed-delay QVNNs with parameter uncertainties are also studied, and the conditions for ensuring the global robust exponential stability of the system are established directly. The adopted approach and the obtained results in this paper complement already the existing ones. Finally, three numerical examples are provided to illustrate the feasibility and the less level conservatism of the main results.

Globally Exponential Stability and Globally Power Stability of Quaternion-Valued Neural Networks With Discrete and Distributed Delays

This paper investigates the stability of a class of quaternion-valued neural networks (QVNNs) with discrete and distributed delays. By decomposing the QVNN and forming an equivalent real-valued vector-matrix differential equation (RVVDE), based on the Lyapunov theory and some matrix inequalities, some sufficient conditions are derived to ensure the existence and uniqueness, the globally exponential stability and the globally power stability of the equilibrium of RVVDE. These conditions also apply to the QVNN. Two numerical examples are given to show the advantage and the effectiveness of the main results.

Stability and stabilization of quaternion-valued neural networks with uncertain time-delayed impulses: Direct quaternion method

In this paper, the exponential stability of impulsive quaternion-valued neural networks (IQVNNs) with time delays is investigated. Both the differential equation and impulses are affected by time-varying delays which may be nonidentical. Uncertain parameters in impulses are also considered. Firstly, the existence and uniqueness of the equilibrium of the IQVNNs are discussed with the help of homeomorphic mapping theorem. Then, by utilizing Lyapunov functions and a newly developed inequality, several sufficient criteria are established in the form of quaternion-valued linear matrix inequalities (LMIs). It should be noted that, compared to most of existing results which are obtained by decomposing quaternion-valued neural networks (QVNNs) into four real-valued neural networks (RVNNs) or two complex-valued neural networks (CVNNs), our results are easier to be verified since the quaternion-valued LMIs exhibit lower dimensions. Then, based on obtained results, one impulsive controller is designed to realize the stabilization of delayed QVNNs. Finally, two numerical examples are presented to verify the effectiveness and merits of the theoretical analysis.

Exponential input-to-state stability of quaternion-valued neural networks with time delay

This paper debated the exponential input-to-state stability (EITSS) of the solution for a kind of quaternion-valued neural networks (QVNNs) with time delay. It fills the blank of QVNN in the aspect of input-to-state stability (ITSS). In virtue of the quaternion multiplication is not suitable for commutative law, QVNN is ordinarily resolved into four real-valued neural networks (RVNNs). Making use of a novel Lyapunov–Krasovskii function and some inequalities, we obtain a little sufficient conditions to assure the considered system is EITSS. Finally, by means of two examples, it is certified that the calculation results in this paper are fine.

Global $\mu$ -Stability of Quaternion-Valued Neural Networks With Unbounded and Asynchronous Time-Varying Delays

In this paper, we investigate the global μ-stability problem of quaternion-valued neural networks (QVNNs) with unbounded and asynchronous time-varying delays. The decomposition of QVNNs is proposed first based on the Hamilton rules to avoid the non-communicative multiplication feature of the quaternion. Instead of establishing the Lyapunov-Krasovskii functional in the form of the Hermitian matrix, we combine the {ξ, ∞}-norm and the Cauchy convergence principle to derive the sufficient conditions that guarantee the existence, uniqueness, and μ-stability of the equilibrium point. The obtained criteria here are milder, owing to the consideration of inhibitory and excitatory between neurons. Finally, a specified example is presented to verify the correctness of the obtained results.

Effects of State-Dependent Impulses on Robust Exponential Stability of Quaternion-Valued Neural Networks Under Parametric Uncertainty.

This paper addresses the state-dependent impulsive effects on robust exponential stability of quaternion-valued neural networks (QVNNs) with parametric uncertainties. In view of the noncommutativity of quaternion multiplication, we have to separate the concerned quaternion-valued models into four real-valued parts. Then, several assumptions ensuring every solution of the separated state-dependent impulsive neural networks intersects each of the discontinuous surface exactly once are proposed. In the meantime, by applying the B -equivalent method, the addressed state-dependent impulsive models are reduced to fixed-time ones, and the latter can be regarded as the comparative systems of the former. For the subsequent analysis, we proposed a novel norm inequality of block matrix, which can be utilized to analyze the same stability properties of the separated state-dependent impulsive models and the reduced ones efficaciously. Afterward, several sufficient conditions are well presented to guarantee the robust exponential stability of the origin of the considered models; it is worth mentioning that two cases of addressed models are analyzed concretely, that is, models with exponential stable continuous subsystems and destabilizing impulses, and models with unstable continuous subsystems and stabilizing impulses. In addition, an application case corresponding to the stability problem of models with unstable continuous subsystems and stabilizing impulses for state-dependent impulse control to robust exponential synchronization of QVNNs is considered summarily. Finally, some numerical examples are proffered to illustrate the effectiveness and correctness of the obtained results.

Stability of Quaternion-Valued Neural Networks with Mixed Delays

In this paper, we investigate the dynamic behaviors of quaternion-valued recurrent neural networks with mixed time delays. On the basis of Brouwer’s fixed point theorem, quaternion-valued variation parameter and quaternion-modulus inequality technique, some sufficient conditions are derived for assuring existence and stability of the equilibrium point of quaternion-valued recurrent neural networks with time-varying delays and distributed delays. Finally, an example is used to illustrate the effectiveness of the obtained results.

Robust stability analysis of quaternion-valued neural networks via LMI approach

This paper is concerned with the issue of robust stability for quaternion-valued neural networks (QVNNs) with leakage, discrete and distributed delays by employing a linear matrix inequality (LMI) approach. Based on the homeomorphic mapping theorem, the quaternion matrix theorem and the Lyapunov theorem, some criteria are developed in the form of real-valued LMIs for guaranteeing the existence, uniqueness, and global robust stability of the equilibrium point of the delayed QVNNs. Two numerical examples are provided to demonstrate the effectiveness of the obtained results.

Stability Analysis of Quaternion-Valued Neural Networks: Decomposition and Direct Approaches.

In this paper, we investigate the global stability of quaternion-valued neural networks (QVNNs) with time-varying delays. On one hand, in order to avoid the noncommutativity of quaternion multiplication, the QVNN is decomposed into four real-valued systems based on Hamilton rules: $ij=-ji=k,~jk=-kj=i$ , $ki=-ik=j$ , $i^{2}=j^{2}=k^{2}=ijk=-1$ . With the Lyapunov function method, some criteria are, respectively, presented to ensure the global $\mu $ -stability and power stability of the delayed QVNN. On the other hand, by considering the noncommutativity of quaternion multiplication and time-varying delays, the QVNN is investigated directly by the techniques of the Lyapunov-Krasovskii functional and the linear matrix inequality (LMI) where quaternion self-conjugate matrices and quaternion positive definite matrices are used. Some new sufficient conditions in the form of quaternion-valued LMI are, respectively, established for the global $\mu $ -stability and exponential stability of the considered QVNN. Besides, some assumptions are presented for the two different methods, which can help to choose quaternion-valued activation functions. Finally, two numerical examples are given to show the feasibility and the effectiveness of the main results.

Robust stability analysis of quaternion-valued neural networks with time delays and parameter uncertainties

This paper addresses the problem of robust stability for quaternion-valued neural networks (QVNNs) with leakage delay, discrete delay and parameter uncertainties. Based on Homeomorphic mapping theorem and Lyapunov theorem, via modulus inequality technique of quaternions, some sufficient conditions on the existence, uniqueness, and global robust stability of the equilibrium point are derived for the delayed QVNNs with parameter uncertainties. Furthermore, as direct applications of these results, several sufficient conditions are obtained for checking the global robust stability of QVNNs without leakage delay as well as complex-valued neural networks (CVNNs) with both leakage and discrete delays. Finally, two numerical examples are provided to substantiate the effectiveness of the proposed results.

Global [formula omitted]stability of quaternion-valued neural networks with non-differentiable time-varying delays

In the paper, the quaternion-valued neural networks (QVNNs) with non-differentiable time-varying delays are considered. Firstly, by using the method of plural decomposition, we decompose the QVNNs into two complex-valued neural networks. Some sufficient criteria in linear matrix inequality (LMI) form are derived to guarantee the existence and uniqueness of the equilibrium point for considered QVNNs by using the homeomorphism mapping principle of complex domain. Secondly, based on applying the free weighting matrix method and constructing appropriate Lyapunov–Krasovskii functional, several conditions are established in LMIs to ensure the the global μ−stability of QVNNs. Finally, by employing the predictor-corrector approach, two numerical examples are provided to show the feasibility and availability of the obtained result.