New Criteria on Stability of Dynamic Memristor Delayed Cellular Neural Networks

Dynamic memristor (DM)-cellular neural networks (CNNs), which replace a linear resistor with flux-controlled memristor in the architecture of each cell of traditional CNNs, have attracted researchers' attention. Compared with common neural networks, the DM-CNNs have an outstanding merit: when a steady state is reached, all voltages, currents, and power consumption of DM-CNNs disappeared, in the meantime, the memristor can store the computation results by serving as nonvolatile memories. The previous study on stability of DM-CNNs rarely considered time delay, while delay is quite common and highly impacts the stability of the system. Thus, taking the time delay effect into consideration, we extend the original system to DM-D(delay)CNNs model. By using the Lyapunov method and the matrix theory, some new sufficient conditions for the global asymptotic stability and global exponential stability with a known convergence rate of DM-DCNNs are obtained. These criteria generalized some known conclusions and are easily verified. Moreover, we find DM-DCNNs have 3ⁿ equilibrium points (EPs) and 2ⁿ of them are locally asymptotically stable. These results are obtained via a given constitutive relation of memristor and the appropriate division of state space. Combine with these theoretical results, the applications of DM-DCNNs can be extended to other fields, such as associative memory, and its advantage can be used in a better way. Finally, numerical simulations are offered to illustrate the effectiveness of our theoretical results.

Multistability and associative memory of neural networks with Morita-like activation functions

This paper presents the multistability analysis and associative memory of neural networks (NNs) with Morita-like activation functions. In order to seek larger memory capacity, this paper proposes Morita-like activation functions. In a weakened condition, this paper shows that the NNs with n-neurons have (2m+1)ⁿ equilibrium points (Eps) and (m+1)ⁿ of them are locally exponentially stable, where the parameter m depends on the Morita-like activation functions, called Morita parameter. Also the attraction basins are estimated based on the state space partition. Moreover, this paper applies these NNs into associative memories (AMs). Compared with the previous related works, the number of Eps and AM's memory capacity are extensively increased. The simulation results are illustrated and some reliable associative memories examples are shown at the end of this paper.

Improved approach to the problem of the global Mittag-Leffler synchronization for fractional-order multidimension-valued BAM neural networks based on new inequalities

This paper studies the problem of the global Mittag-Leffler synchronization for fractional-order multidimension-valued BAM neural networks (FOMVBAMNNs) with general activation functions (AFs). First, the unified model is established for the researched systems of FOMVBAMNNs which can be turned into the corresponding multidimension-valued systems as long as the state variables, the connection weights and the AFs of the neural networks are valued to be real, complex, or quaternion. Then, without any decomposition, the criteria in unified form are derived by constructing the new Lyapunov-Krasovskii functionals (LKFs) in vector form, combining two new inequalities and considering the easy controllers. It is worth mentioning that the obtained criteria have many advantages in higher flexibility, more diversity, smaller computation, and lower conservatism. Finally, a simulation example is provided to illustrate the availability and improvements of the acquired results.

New Criteria for Stability of Neutral-Type Neural Networks With Multiple Time Delays

This research work studies stability problems for more general models of neutral-type neural systems where both neuron states and the time derivative of neuron states involve multiple delays. Some new sufficient criterion is presented, which guarantee the existence, uniqueness, and global asymptotic stability of equilibrium points of the considered neural network model. These obtained stability conditions, which can be applied to some larger classes of general neural network models, are based on the analysis of a new and improved suitable Lyapunov functional. The proposed conditions are independent of time delay parameters and can be easily justified by examining some certain relationships among the relevant neural network parameters. This paper also shows that the obtained stability criteria can be considered as the generalization of some previously reported corresponding stability conditions for neural networks, including multiple time delay parameters.

Investigating Echo-State Networks Dynamics by Means of Recurrence Analysis

In this paper, we elaborate over the well-known interpretability issue in echo-state networks (ESNs). The idea is to investigate the dynamics of reservoir neurons with time-series analysis techniques developed in complex systems research. Notably, we analyze time series of neuron activations with recurrence plots (RPs) and recurrence quantification analysis (RQA), which permit to visualize and characterize high-dimensional dynamical systems. We show that this approach is useful in a number of ways. First, the 2-D representation offered by RPs provides a visualization of the high-dimensional reservoir dynamics. Our results suggest that, if the network is stable, reservoir and input generate similar line patterns in the respective RPs. Conversely, as the ESN becomes unstable, the patterns in the RP of the reservoir change. As a second result, we show that an RQA measure, called , is highly correlated with the well-established maximal local Lyapunov exponent. This suggests that complexity measures based on RP diagonal lines distribution can quantify network stability. Finally, our analysis shows that all RQA measures fluctuate on the proximity of the so-called edge of stability, where an ESN typically achieves maximum computational capability. We leverage on this property to determine the edge of stability and show that our criterion is more accurate than two well-known counterparts, both based on the Jacobian matrix of the reservoir. Therefore, we claim that RPs and RQA-based analyses are valuable tools to design an ESN, given a specific problem.

Delay-Dependent Global Exponential Stability for Delayed Recurrent Neural Networks

This paper deals with the global exponential stability for delayed recurrent neural networks (DRNNs). By constructing an augmented Lyapunov-Krasovskii functional and adopting the reciprocally convex combination approach and Wirtinger-based integral inequality, delay-dependent global exponential stability criteria are derived in terms of linear matrix inequalities. Meanwhile, a general and effective method on global exponential stability analysis for DRNNs is given through a lemma, where the exponential convergence rate can be estimated. With this lemma, some global asymptotic stability criteria of DRNNs acquired in previous studies can be generalized to global exponential stability ones. Finally, a frequently utilized numerical example is carried out to illustrate the effectiveness and merits of the proposed theoretical results.

Synchronization of Reaction-Diffusion Neural Networks With Dirichlet Boundary Conditions and Infinite Delays

This paper is concerned with synchronization for a class of reaction-diffusion neural networks with Dirichlet boundary conditions and infinite discrete time-varying delays. By utilizing theories of partial differential equations, Green's formula, inequality techniques, and the concept of comparison, algebraic criteria are presented to guarantee master-slave synchronization of the underlying reaction-diffusion neural networks via a designed controller. Additionally, sufficient conditions on exponential synchronization of reaction-diffusion neural networks with finite time-varying delays are established. The proposed criteria herein enhance and generalize some published ones. Three numerical examples are presented to substantiate the validity and merits of the obtained theoretical results.

Stability Analysis of Neural Networks With Two Delay Components Based on Dynamic Delay Interval Method

In this paper, a dynamic delay interval (DDI) method is proposed to deal with the stability problem of neural networks with two delay components. This method extends the fixed interval of a time-varying delay to a dynamic one, which relaxes the restriction on upper and lower bounds of the delay intervals. Combining the reciprocally convex combination technique and Wirtinger integral inequality, the DDI method leads to some much less conservative delay-dependent stability criteria based on a linear matrix inequality for neural networks with two delay components. Furthermore, the criteria for the system with a single time-varying delay are provided. Some examples are given to illustrate the effectiveness of the obtained results.

Exponential stability and periodicity of memristor-based recurrent neural networks with time-varying delays

In this paper, the stability and periodicity of memristor-based neural networks with time-varying delays are studied. Based on linear matrix inequalities, differential inclusion theory and by constructing proper Lyapunov functional approach and using linear matrix inequality, some sufficient conditions are obtained for the global exponential stability and periodic solutions of memristor-based neural networks. Finally, two illustrative examples are given to demonstrate the results.

Synchronization Control of Neural Networks With State-Dependent Coefficient Matrices

This brief is concerned with synchronization control of a class of neural networks with state-dependent coefficient matrices. Being different from the existing drive-response neural networks in the literature, a novel model of drive-response neural networks is established. The concepts of uniformly ultimately bounded (UUB) synchronization and convex hull Lyapunov function are introduced. Then, by using the convex hull Lyapunov function approach, the UUB synchronization design of the drive-response neural networks is proposed, and a delay-independent control law guaranteeing the bounded synchronization of the neural networks is constructed. All present conditions are formulated in terms of bilinear matrix inequalities. By comparison, it is shown that the neural networks obtained in this brief are less conservative than those ones in the literature, and the bounded synchronization is suitable for the novel drive-response neural networks. Finally, an illustrative example is given to verify the validity of the obtained results.

Synchronization of a Class of Switched Neural Networks with Time-Varying Delays via Nonlinear Feedback Control

This paper is concerned with the synchronization problem for a class of switched neural networks (SNNs) with time-varying delays. First, a new crucial lemma which includes and extends the classical exponential stability theorem is constructed. Then by using the lemma, new algebraic criteria of ψ -type synchronization (synchronization with general decay rate) for SNNs are established via the designed nonlinear feedback control. The ψ -type synchronization which is in a general framework is obtained by introducing a ψ -type function. It contains exponential synchronization, polynomial synchronization, and other synchronization as its special cases. The results of this paper are general, and they also complement and extend some previous results. Finally, numerical simulations are carried out to demonstrate the effectiveness of the obtained results.

Mean-square exponential input-to-state stability of delayed Cohen-Grossberg neural networks with Markovian switching based on vector Lyapunov functions

This paper studies the mean-square exponential input-to-state stability of delayed Cohen-Grossberg neural networks with Markovian switching. By using the vector Lyapunov function and property of M-matrix, two generalized Halanay inequalities are established. By means of the generalized Halanay inequalities, sufficient conditions are also obtained, which can ensure the exponential input-to-state stability of delayed Cohen-Grossberg neural networks with Markovian switching. Two numerical examples are given to illustrate the efficiency of the derived results.

Finite-Time Stabilizability and Instabilizability of Delayed Memristive Neural Networks With Nonlinear Discontinuous Controller

This paper is concerned about the finite-time stabilizability and instabilizability for a class of delayed memristive neural networks (DMNNs). Through the design of a new nonlinear controller, algebraic criteria based on M -matrix are established for the finite-time stabilizability of DMNNs, and the upper bound of the settling time for stabilization is estimated. In addition, finite-time instabilizability algebraic criteria are also established by choosing different parameters of the same nonlinear controller. The effectiveness and the superiority of the obtained results are supported by numerical simulations.

Passivity and Passification of Memristor-Based Recurrent Neural Networks With Additive Time-Varying Delays

This paper presents a new design scheme for the passivity and passification of a class of memristor-based recurrent neural networks (MRNNs) with additive time-varying delays. The predictable assumptions on the boundedness and Lipschitz continuity of activation functions are formulated. The systems considered here are based on a different time-delay model suggested recently, which includes additive time-varying delay components in the state. The connection between the time-varying delay and its upper bound is considered when estimating the upper bound of the derivative of Lyapunov functional. It is recognized that the passivity condition can be expressed in a linear matrix inequality (LMI) format and by using characteristic function method. For state feedback passification, it is verified that it is apathetic to use immediate or delayed state feedback. By constructing a Lyapunov-Krasovskii functional and employing Jensen's inequality and reciprocal convex combination technique together with a tighter estimation of the upper bound of the cross-product terms derived from the derivatives of the Lyapunov functional, less conventional delay-dependent passivity criteria are established in terms of LMIs. Moreover, second-order reciprocally convex approach is employed for deriving the upper bound for terms with inverses of squared convex parameters. The model based on the memristor with additive time-varying delays widens the application scope for the design of neural networks. Finally, pertinent examples are given to show the advantages of the derived passivity criteria and the significant improvement of the theoretical approaches.

Quasi-Ideal Memory System

The definition for ideal memory system is so strict that some physical elements cannot exist in the real world. In this paper, an ideal memory system can be extended to generate 15 different kinds of quasi-ideal memory systems, which are included in memory systems as its special cases and are different from ideal memory system. For a system to be a quasi-ideal memory system, it should show three unique fingerprints: 1) the pinched hysteretic loop of a quasi-ideal memory system must be odd symmetrical in the plane; 2) the pinched hysteretic loop of a quasi-ideal memory system must be "self-crossing"; and 3) the slope of tangent line for the pinched hysteresis loop must be strictly monotone in a given period.

Convergence analysis of the FOCUSS algorithm

Focal Underdetermined System Solver (FOCUSS) is a powerful and easy to implement tool for basis selection and inverse problems. One of the fundamental problems regarding this method is its convergence, which remains unsolved until now. We investigate the convergence of the FOCUSS algorithm in this paper. We first give a rigorous derivation for the FOCUSS algorithm by exploiting the auxiliary function. Following this, we further prove its convergence by stability analysis.

Passivity of switched recurrent neural networks with time-varying delays

This paper is concerned with the passivity analysis for switched neural networks subject to stochastic disturbances and time-varying delays. First, using the multiple Lyapunov functions method, a state-dependent switching law is designed to present a stochastic passivity condition. Second, a hysteresis switching law involving both the current state and the previous value of the switching signal are presented to avoid chattering resulted from the state-dependent switching. Third, based on the average dwell-time approach, a class of switching signals is determined to guarantee the switched neural network stochastically passive. Finally, three numerical examples are provided to illustrate the characteristics of three proposed switching laws.

Global robust stability of complex-valued recurrent neural networks with time-delays and uncertainties

This paper focuses on the existence, uniqueness and global robust stability of equilibrium point for complex-valued recurrent neural networks with multiple time-delays and under parameter uncertainties with respect to two activation functions. Two sufficient conditions for robust stability of the considered neural networks are presented and established in two new time-independent relationships between the network parameters of the neural system. Finally, three illustrative examples are given to demonstrate the theoretical results.

Further results on robustness analysis of global exponential stability of recurrent neural networks with time delays and random disturbances

In this paper, further results on robustness analysis of global exponential stability of recurrent neural networks (RNNs) subjected to time delays and random disturbances are provided. Novel exponential stability criteria for the RNNs are derived, and upper bounds of the time delay and noise intensity are characterized by solving transcendental equations containing adjustable parameters. Through the selection of the adjustable parameters, the upper bounds are improved. It shows that our results generalize and improve the corresponding results of recent works. In addition, some numerical examples are given to show the effectiveness of the results we obtained.

Robustness analysis for connection weight matrices of global exponential stability of stochastic recurrent neural networks

This paper analyzes the robustness of global exponential stability of stochastic recurrent neural networks (SRNNs) subject to parameter uncertainty in connection weight matrices. Given a globally exponentially stable stochastic recurrent neural network, the problem to be addressed here is how much parameter uncertainty in the connection weight matrices that the neural network can remain to be globally exponentially stable. We characterize the upper bounds of the parameter uncertainty for the recurrent neural network to sustain global exponential stability. A numerical example is provided to illustrate the theoretical result.

Design of delay-dependent state estimator for discrete-time recurrent neural networks with interval discrete and infinite-distributed time-varying delays

The state estimation problem for discrete-time recurrent neural networks with both interval discrete and infinite-distributed time-varying delays is studied in this paper, where interval discrete time-varying delay is in a given range. The activation functions are assumed to be globally Lipschitz continuous. A delay-dependent condition for the existence of state estimators is proposed based on new bounding techniques. Via solutions to certain linear matrix inequalities, general full-order state estimators are designed that ensure globally asymptotic stability. The significant feature is that no inequality is needed for seeking upper bounds for the inner product between two vectors, which can reduce the conservatism of the criterion by employing the new bounding techniques. Two illustrative examples are given to demonstrate the effectiveness and applicability of the proposed approach.

Global stability of complex-valued recurrent neural networks with time-delays

Since the last decade, several complex-valued neural networks have been developed and applied in various research areas. As an extension of real-valued recurrent neural networks, complex-valued recurrent neural networks use complex-valued states, connection weights, or activation functions with much more complicated properties than real-valued ones. This paper presents several sufficient conditions derived to ascertain the existence of unique equilibrium, global asymptotic stability, and global exponential stability of delayed complex-valued recurrent neural networks with two classes of complex-valued activation functions. Simulation results of three numerical examples are also delineated to substantiate the effectiveness of the theoretical results.