Memristive Neural Networks Research Articles

Unified analysis on multistablity of fraction-order multidimensional-valued memristive neural networks

This article provides a unified analysis of the multistability of fraction-order multidimensional-valued memristive neural networks (FOMVMNNs) with unbounded time-varying delays. Firstly, based on the knowledge of fractional differentiation and memristors, a unified model is established. This model is a unified form of real-valued, complex-valued, and quaternion-valued systems. Then, based on a unified method, the number of equilibrium points for FOMVMNNs is discussed. The sufficient conditions for determining the number of equilibrium points have been obtained. By using 1-norm to construct Lyapunov functions, the unified criteria for multistability of FOMVMNNs are obtained, these criteria are less conservative and easier to verify. Moreover, the attraction basins of the stable equilibrium points are estimated. Finally, two numerical simulation examples are provided to verify the correctness of the results.

Adaptive Sliding Mode Fixed-/Preassigned-Time Synchronization of Stochastic Memristive Neural Networks with Mixed-Delays

The paper addresses the fixed-/preassigned-time synchronization of stochastic memristive neural networks (MNNs) with uncertain parameters and mixed delays. Adaptive sliding mode control (ASMC) technology is mainly utilized. First, a proper sliding surface is constructed and the adaptive laws are given. Also, the synchronization control scheme is designed, which can ensure error system to realize fixed-time stability. Second, preassigned-time sliding mode control scheme is mainly provided to realize fast synchronization of MNNs. The presented theoretical methods can guarantee the error system convergence and stability for reaching and sliding mode within preassigned-time. And the synchronization criteria and explicit expression of settling time (ST) are acquired, where ST is not related with initial values and controller parameters but can be predefined perferentially. Finally, the calculation example is offered to interpret the practicability and availability of the innovations in this paper.

Global Synchronization of Fractional-Order Memristor Neural Networks with Time-Varying Delays and Distributed Delays

Global Synchronization of Fractional-Order Memristor Neural Networks with Time-Varying Delays and Distributed Delays

Bipartite synchronization for coupled memristive neural networks: Memory-based dynamic updating law

In this paper, bipartite synchronization for memristive neural networks with multi-delay couplings is investigated. The evaluation index of unbounded coupling delays on synchronization could be quantitatively analyzed by considering proportional delay, which will undoubtedly and strongly impede synchronous behavior. By simultaneously taking synchronization and anti-synchronization patterns into account, a novel impulsive controller with a signed form is elaborately designed. For the purpose of selecting suitable impulsive instants, a dynamic self-triggered mechanism is introduced. Additionally, to mitigate the possible risk of the dynamic mechanism transitioning into a static mechanism in exceptional scenarios, a memory-based adaptive updating law is therefore proposed in this paper. It should be noted that the adaptive control related dynamic parameters considered in this paper are in a non-monotonic form. By utilizing Lyapunov stability theorem, parameter variation approach and contradiction analysis method, sufficient conditions for ensuring the synchronization are successfully derived. Finally, two experiments are presented to demonstrate the practicability of the derived results.

Adaptive protocol-based control for reaction-diffusion memristive neural networks with semi-Markov switching parameters

This study explores the asynchronous control of reaction-diffusion memristive neural networks (RDMNNs) using an innovative adaptive event-triggered protocol. The unique characteristic of RDMNNs is captured through a semi-Markov process model, wherein the probability density function of the duration time is contingent on two consecutive modes. A novel adaptive event-triggered strategy, specifically designed for the semi-Markov switching signal, is introduced to effectively reduce the network's bandwidth usage. The determination of thresholds in the adaptive triggering criterion is intricately associated with the system state residuals. Due to the mismatch between the controller and the RDMNNs, the protocol-based controller operates asynchronously. This asynchronous operation is characterized by a hidden semi-Markovian model. Utilizing stochastic Lyapunov functions that correlate with the detected and system modes, several sufficient criteria for designing an effective asynchronous controller are provided, thereby ensuring the stochastic stability of the system. Finally, the feasibility of the proposed scheme is validated through a simulated example.

Global exponential synchronization of BAM memristive neural networks with mixed delays and reaction–diffusion terms

Based on m-norm, this paper investigates global exponential synchronization (GES) for BAM memristive neural networks (BAMMNNs) with mixed delays and reaction–diffusion (RD) terms. Different from the existing literatures, this paper discusses the GES of the NNs based on a new integral inequality with infinite distributed delay. This method is based on inequality technique and comparison principle, which makes the form of Lyapunov function and controller more simple. Next, by introducing two different control strategies and the concept of driven response, two sufficient conditions are got to ensure GES of the proposed system. It is noteworthy that the results obtained by algebraic inequality are extension of the previous conclusions. Finally, two instances verify the correctness of the conclusions.

Dynamic Event-Triggered Control for GSES of Memristive Neural Networks Under Multiple Cyber-Attacks.

In this article, the dynamic event-triggered control problem of memristive neural networks (MNNs) under multiple cyber-attacks is considered. A novel dynamic event-triggering scheme (DETS) and the corresponding event-triggered controller are proposed by taking into consideration both denial-of-service and deception attacks (DoS-DAs). Then, a key lemma is established to show that the dynamic event-triggered controller can be used to solve the globally stochastically exponential stability (GSES) issue of concerned MNN under multiple cyber-attacks. Meanwhile, a novel Lyapunov functional is proposed based on the actual sampling pattern. It is shown that under our proposed dynamic event-triggered controller and Lyapunov functional, the concerned MNN can achieve GSES in the presence of DoS-DAs. In addition, our results include relevant results on event-triggered control of MNN with static event-triggering scheme (SETS) or without cyber-attacks as special cases. The effectiveness of the proposed event-triggered controller under multiple cyber-attacks is illustrated by a simulation example.

A Global Self-Attention Memristive Neural Network for Image Restoration

A Global Self-Attention Memristive Neural Network for Image Restoration

State Estimation for Delayed Memristive Neural Networks With Multichannel Round-Robin Protocol and Multimodal Injection Attacks

State Estimation for Delayed Memristive Neural Networks With Multichannel Round-Robin Protocol and Multimodal Injection Attacks

General Decay Synchronization of State and Spatial Diffusion Coupled Delayed Memristive Neural Networks With Reaction-diffusion Terms

General Decay Synchronization of State and Spatial Diffusion Coupled Delayed Memristive Neural Networks With Reaction-diffusion Terms

Dynamics of heterogeneous Hopfield neural network with adaptive activation function based on memristor

Memristor and activation function are two important nonlinear factors of the memristive Hopfield neural network. The effects of different memristors on the dynamics of Hopfield neural networks have been studied by many researchers. However, less attention has been paid to the activation function. In this paper, we present a heterogeneous memristive Hopfield neural network with neurons using different activation functions. The activation functions include fixed activation functions and an adaptive activation function, where the adaptive activation function is based on a memristor. The theoretical and experimental study of the neural network’s dynamics has been conducted using phase portraits, bifurcation diagrams, and Lyapunov exponents spectras. Numerical results show that complex dynamical behaviors such as multi-scroll chaos, transient chaos, state jumps and multi-type coexisting attractors can be observed in the heterogeneous memristive Hopfield neural network. In addition, the hardware implementation of memristive Hopfield neural network with adaptive activation function is designed and verified. The experimental results are in good agreement with those obtained using numerical simulations.

Design and analysis of a memristive Hopfield switching neural network and application to privacy protection

Design and analysis of a memristive Hopfield switching neural network and application to privacy protection

Sliding mode control for uncertain fractional-order reaction–diffusion memristor neural networks with time delays

This paper investigates a sliding mode control method for a class of uncertain delayed fractional-order reaction–diffusion memristor neural networks. Different from most existing literature on sliding mode control for fractional-order reaction–diffusion systems, this study constructs a linear sliding mode switching function and designs the corresponding sliding mode control law. The sufficient theory for the globally asymptotic stability of the sliding mode dynamics are provided, and it is proven that the sliding mode surface is finite-time reachable under the proposed control law, with an estimate of the maximum reaching time. Finally, a numerical test is presented to validate the effectiveness of the theoretical analysis.

Time-Varying Function Matrix Projection Synchronization of Caputo Fractional-Order Uncertain Memristive Neural Networks with Multiple Delays via Mixed Open Loop Feedback Control and Impulsive Control

This paper shows solicitude for the generalized projective synchronization of Caputo fractional-order uncertain memristive neural networks (FOUMNNs) with multiple delays. By extending the constant scale factor to the time-varying function matrix, we establish an extraordinary synchronization mode called time-varying function matrix projection synchronization (TFMPS), which is a generalized version of traditional matrix projection synchronization, modified projection synchronization, complete synchronization, and anti-synchronization. To achieve the goal of TFMPS, we design a novel mixed controller including the open loop feedback control and impulsive control, which employs the state information in the time-delayed interval and the sampling information at the impulse instants. It has a prominent advantage that impulse intervals are not restricted by time delays. To establish the connection between the error system and the auxiliary system, a generalized fractional-order comparison theorem with time-varying coefficients and impulses is established. Applying the stability theory, the comparison theorem, and the Laplace transform, new synchronization criteria of FOUMNNs are acquired under the mixed impulsive control schemes, and the derived synchronization theorem and corollary can effectively expand the correlative synchronization achievements of fractional-order systems.

Synchronization of Fractional Delayed Memristive Neural Networks with Jump Mismatches via Event-Based Hybrid Impulsive Controller

This study investigates the asymptotic synchronization in fractional memristive neural networks of the Riemann–Liouville type, considering mixed time delays and jump mismatches. Addressing the challenges associated with discrepancies in the circuit switching speed and the accuracy of the memristor, this paper introduces an enhanced model that effectively navigates these complexities. We propose two novel event-based hybrid impulsive controllers, each characterized by unique triggering conditions. Utilizing advanced techniques in inequality and hybrid impulsive control, we establish the conditions necessary for achieving synchronization through innovative Lyapunov functions. Importantly, the developed controllers are theoretically optimized to minimize control costs, an essential consideration for their practical deployment. Finally, the effectiveness of our proposed approach is demonstrated through two illustrative simulation examples.

Quantized filtering for switched memristive neural networks against deception attacks

This paper deals with the quantized mixed H∞/L2−L∞ filtering issue for switched memristive neural networks in the presence of deception attacks, in which the switching of parameters is not only subject to neural states, but also to the persistent dwell-time switching rule in the continuous-time case. First, a switched dynamic quantizer is utilized to quantize the measurement output before being transmitted to the filter. Second, deception attacks governed by a Bernoulli distribution are considered during the quantized output transmission. Then, in virtue of the Lyapunov stability theory together with stochastic analysis theory, a sufficient condition is given to ensure the global uniform asymptotic stability in the mean-square sense for the filtering error system with a mixed H∞/L2−L∞ performance. Furthermore, a co-design scheme for the desired mode-dependent filter gain and dynamic parameter is provided. Ultimately, the effectiveness of the proposed method is verified by a numerical example.

Probability‐guaranteed encoding–decoding‐based state estimation for delayed memristive neutral networks with event‐triggered mechanism

SummaryThis article handles the probability‐guaranteed state estimation problem for a class of nonlinear memristive neural networks (MNNs) by using an event‐triggered mechanism. Both time‐varying delays and incomplete measurements are considered in the MNNs dynamics. To mitigate the impact of limited communication bandwidth, a communication protocol is proposed that incorporates an encoding–decoding technique in addition to an event‐triggered scheme. The aim is to devise a state estimator that can estimate the states of MNNs, ensuring that the state estimation error falls within the required ellipsoidal area with a desired chance. We obtain sufficient conditions for the feasibility of the addressed problem, where the requested gains can be found iteratively by solving certain convex optimization problems. On the basis of the proposed framework, some issues are further presented to determine locally optimal estimator parameters according to different specifications. Finally, we utilize an illustrative numerical example to show the validity of our provided theoretical results.

A novel memristor Hopfield neural network with homogeneous coexisting multi-scroll attractors

Abstract Compared to conventional single-scroll or double-scroll attractors, multi-scroll chaotic attractors possess wide potential for application due to their adjustability and complex topology. However, neural network models for generating multiple scrolls are often implemented using memristors with piecewise nonlinear functions. To further explore multi-scroll attractors with different working mechanisms,a unique memristor containing a group of hyperbolic tangent functions is designed and then applied in a three-dimensional Hopfield neural network (HNN). The proposed memristive Hopfield neural network (MHNN) has multi-scroll chaotic attractors, where the number and parity of the scrolls be changed by adjusting the control parameters of the memristor. The complex dynamical behaviors of MHNN are studied by utilizing diverse numerical modeling approaches like bifurcation diagrams, Lyapunov exponents and phase plot. In addition, the proposed MHNN also has a complicated offset boosting coexisting behavior. By selecting suitable parameters, multiple coexisting chaotic attractors could be obtained. Homogeneous coexisting multi-scroll attractors can be shifted in multiple directions including unidirectional, planar and spatial ones. Moreover, theoretically speaking, there could be an infinite number of coexisting attractors. Finally, experimental results are validated through numerical simulations and circuit experiments to confirm the feasibility of the proposed MHNN model.

Dissipative control for quaternion-valued fuzzy memristive neural networks: Nonlinear scalarization approach

This paper deals with the dissipative control for a class of quaternion-valued fuzzy memristive neural networks. By constructing proper Lyapunov functionals and using adaptive controller, the strictly (Q,S,R)-dissipative are characterized parametrically. Then, based on the algebraic inequality and linear matrix inequality (LMI) approach, sufficient conditions for the existence of the dissipative controllers are obtained. In addition, the nonlinear scalarization approach is developed, which can be employed to compare the “size” of two different quaternions, in this way, the convex closure proposed by the quaternion weights are meaningful. Finally, simulation examples are given to show the efficiency of the proposed methods.

HDR vision sensor with neuro-memristive skin detection for edge computing

Human skin classification is an essential task for several machine vision applications such as human-machine interfaces, people/object tracking, and classification. In this paper, we describe a hybrid CMOS/memristor vision sensor architecture embedding skin detection over a wide dynamic range. In-sensor RGB to rg-chromaticity color-space conversion is executed on-the-fly through a pixel-level automatic exposure time control. Each pixel of the array delivers two pre-filtered analog signals, the r and g values, suitable for being efficiently classified as skin or non-skin through an analog memristive neural network (NN), without the need for any further signal processing. Moreover, we study the NN performance and theorize how it should be added in the hardware. The skin classifier is organized in an array of column-level memristor-based NN to exploit the nano-scale device characteristics and non-volatile analog memory capabilities, making the proposed sensor architecture highly flexible, customizable for various use-case scenarios, and low-power. The output is a skin bitmap that is robust against variations of the illuminant color and intensity.