Quasi-Synchronization of Delayed Memristive Neural Networks via Region-Partitioning-Dependent Intermittent Control

Practical Fixed-Time Bipartite Synchronization of Uncertain Coupled Neural Networks Subject to Deception Attacks via Dual-Channel Event-Triggered Control

This article investigates the practical fixed-time synchronization of uncertain coupled neural networks via dual-channel event-triggered control. Contrary to some previous studies, the bipartite synchronization of signed graphs representing cooperative and antagonistic interactions is studied. The communication channel is introduced into deception attacks, which are described by Bernoulli's stochastic variables. Based on the concept of two channels, event-triggered mechanisms are designed for sensor-to-controller and controller-to-actuator channels to reduce communication consumption and controller update consumption as much as possible. Lyapunov and comparison theories are used to derive synchronization criteria and explicit expression of settling time. An example of Chua's circuit system is presented to demonstrate the feasibility of the obtained theoretical results.

Feedback stabilization of probabilistic finite state machines based on deep Q-network

Background

As an important mathematical model, the finite state machine (FSM) has been used in many fields, such as manufacturing system, health care, and so on. This paper analyzes the current development status of FSMs. It is pointed out that the traditional methods are often inconvenient for analysis and design, or encounter high computational complexity problems when studying FSMs.

Method

The deep Q-network (DQN) technique, which is a model-free optimization method, is introduced to solve the stabilization problem of probabilistic finite state machines (PFSMs). In order to better understand the technique, some preliminaries, including Markov decision process, ϵ-greedy strategy, DQN, and so on, are recalled.

Results

First, a necessary and sufficient stabilizability condition for PFSMs is derived. Next, the feedback stabilization problem of PFSMs is transformed into an optimization problem. Finally, by using the stabilizability condition and deep Q-network, an algorithm for solving the optimization problem (equivalently, computing a state feedback stabilizer) is provided.

Discussion

Compared with the traditional Q learning, DQN avoids the limited capacity problem. So our method can deal with high-dimensional complex systems efficiently. The effectiveness of our method is further demonstrated through an illustrative example.

A novel associative memory model based on semi-tensor product (STP)

A good intelligent learning model is the key to complete recognition of scene information and accurate recognition of specific targets in intelligent unmanned system. This study proposes a new associative memory model based on the semi-tensor product (STP) of matrices, to address the problems of information storage capacity and association. First, some preliminaries are introduced to facilitate modeling, and the problem of information storage capacity in the application of discrete Hopfield neural network (DHNN) to associative memory is pointed out. Second, learning modes are equivalently converted into their algebraic forms by using STP. A memory matrix is constructed to accurately remember these learning modes. Furthermore, an algorithm for updating the memory matrix is developed to improve the association ability of the model. And another algorithm is provided to show how our model learns and associates. Finally, some examples are given to demonstrate the effectiveness and advantages of our results. Compared with mainstream DHNNs, our model can remember learning modes more accurately with fewer nodes.

Stabilization of Discrete-Time Stochastic Delayed Neural Networks by Intermittent Control

This article investigates the stabilization of discrete-time stochastic neural networks with time-varying delay via aperiodically intermittent control (AIC). A comprehensive analysis of the stabilization of discrete-time delayed systems via AIC is provided, where the Lyapunov function method and the Lyapunov-Krasovskii functional method are investigated, respectively. Then, three stabilization criteria are given, which extend previous works from the continuous-time framework to the discrete-time one, and the average activation time ratio (AATR) of AIC is estimated. It is highlighted that for the Lyapunov-Krasovskii functional method, a more flexible estimation for the AATR can be obtained. Finally, the differences and the advantages of the three stabilization criteria are illustrated by numerical simulations.

Multiple Mismatched Synchronization for Coupled Memristive Neural Networks With Topology-Based Probability Impulsive Mechanism on Time Scales

This article is concerned with the exponential synchronization of coupled memristive neural networks (CMNNs) with multiple mismatched parameters and topology-based probability impulsive mechanism (TPIM) on time scales. To begin with, a novel model is designed by taking into account three types of mismatched parameters, including: 1) mismatched dimensions; 2) mismatched connection weights; and 3) mismatched time-varying delays. Then, the method of auxiliary-state variables is adopted to deal with the novel model, which implies that the presented novel model can not only use any isolated system (regard as a node) in the coupled system to synchronize the states of CMNNs but also can use an external node, that is, not affiliated to the coupled system to synchronize the states of CMNNs. Moreover, the TPIM is first proposed to efficiently schedule information transmission over the network, possibly subject to a series of nonideal factors. The novel control protocol is more robust against these nonideal factors than the traditional impulsive control mechanism. By means of the Lyapunov-Krasovskii functional, robust analysis approach, and some inequality processing techniques, exponential synchronization conditions unifying the continuous-time and discrete-time systems are derived on the framework of time scales. Finally, a numerical example is provided to illustrate the effectiveness of the main results.

Quasisynchronization of Memristive Neural Networks With Communication Delays via Event-Triggered Impulsive Control

This article considers the quasisynchronization of memristive neural networks (MNNs) with communication delays via event-triggered impulsive control (ETIC). In view of the limited communication and bandwidth, we adopt a novel switching event-triggered mechanism (ETM) that not only decreases the times of controller update and the amount of data sent out but also eliminates the Zeno behavior. By using an appropriate Lyapunov function, several algebraic conditions are given for quasisynchronization of MNNs with communication delays. More important, there is no restriction on the derivation of the Lyapunov function, even if it is an increasing function over a period of time. Then, we further propose a switching ETM depending on communication delays and aperiodic sampling, which is more economical and practical and can directly avoid Zeno behavior. Finally, two simulations are presented to validate the effectiveness of the proposed results.

Resilient H∞ State Estimation for Discrete-Time Stochastic Delayed Memristive Neural Networks: A Dynamic Event-Triggered Mechanism

In this article, a resilient H_∞ approach is put forward to deal with the state estimation problem for a type of discrete-time delayed memristive neural networks (MNNs) subject to stochastic disturbances (SDs) and dynamic event-triggered mechanism (ETM). The dynamic ETM is utilized to mitigate unnecessary resource consumption occurring in the sensor-to-estimator communication channel. To guarantee resilience against possible realization errors, the estimator gain is permitted to undergo some norm-bounded parameter drifts. For the delayed MNNs, our aim is to devise an event-based resilient H_∞ estimator that not only resists gain variations and SDs but also ensures the exponential mean-square stability of the resulting estimation error system with a guaranteed disturbance attenuation level. By resorting to the stochastic analysis technique, sufficient conditions are acquired for the expected estimator and, subsequently, estimator gains are obtained via figuring out a convex optimization problem. The validity of the H_∞ estimator is finally shown via a numerical example.

Extended Dissipativity Analysis for Markovian Jump Neural Networks via Double-Integral-Based Delay-Product-Type Lyapunov Functional

This brief studies the problem of extended dissipativity analysis for the Markovian jump neural networks (MJNNs) with time-varying delay. A double-integral-based delay-product-type (DIDPT) Lyapunov functional is first constructed in this brief, which makes full use of the information of time delay. Moreover, some unnecessary constraints on the system structure are removed, which leads to more general results. A numerical example is employed to illustrate the advantages of the proposed method.

Synchronization of recurrent neural networks with unbounded delays and time-varying coefficients via generalized differential inequalities

In this paper, we revisit the drive-response synchronization of a class of recurrent neural networks with unbounded delays and time-varying coefficients, contrary to usual in the literature about time-varying neural networks, the signs of self-feedback coefficients are permitted to be indefinite or the time-varying coefficients can be unbounded. A generalized scalar delay differential inequality considering indefinite self-feedback coefficient and unbounded delay simultaneously is established, which covers the existing result with bounded delay, the applicabilities of the sufficient conditions are discussed. Some novel criteria for network synchronization are then derived by constructing different candidate functions. These results have been improved in some aspects compared with the existing ones. Differential inequality in vector form is also derived to obtain a more refined synchronization criterion which removes some strong assumptions. Three examples are presented to verify the effectiveness and show the superiorities of our theoretical results.

Master-Slave Synchronization of Delayed Neural Networks With Time-Varying Control

This brief investigates the master-slave synchronization problem of delayed neural networks with general time-varying control. Assuming a linear feedback controller with time-varying control gain, the synchronization problem is recast into the stability problem of a delayed system with a time-varying coefficient. The main theorem is established in terms of the time average of the control gain by using the Lyapunov-Razumikhin theorem. Moreover, the proposed framework encompasses some general intermittent control schemes, such as the switched control gain with external disturbance and intermittent control with pulse-modulated gain function, while some useful corollaries are consequently deduced. Interestingly, our theorem also provides a solution for regaining stability under control failure. The validity of the theorem and corollaries is further demonstrated with numerical examples.

Synchronization of memristive neural networks with unknown parameters via event-triggered adaptive control

This paper considers the drive-response synchronization of memristive neural networks (MNNs) with unknown parameters, where the unbounded discrete and bounded distributed time-varying delays are involved. Aiming at the unknown parameters of MNNs, the updating law of weight in response system and the gain of adaptive controller are proposed to realize the synchronization of delayed MNNs. In view of the limited communication and bandwidth, the event-triggered mechanism is introduced to adaptive control, which not only decreases the times of controller update and the amount of data sending out but also enables synchronization when parameters of MNNs are unknown. In addition, a relative threshold strategy, which is relative to fixed threshold strategy, is proposed to increase the inter-execution intervals and to improve the control effect. When the parameters of MNNs are known, the algebraic criteria of synchronization are established via event-triggered state feedback control by exploiting inequality techniques and calculus theorems. Finally, one simulation is presented to validate the effectiveness of the proposed results.

Memristive Quantized Neural Networks: A Novel Approach to Accelerate Deep Learning On-Chip

Existing deep neural networks (DNNs) are computationally expensive and memory intensive, which hinder their further deployment in novel nanoscale devices and applications with lower memory resources or strict latency requirements. In this paper, a novel approach to accelerate on-chip learning systems using memristive quantized neural networks (M-QNNs) is presented. A real problem of multilevel memristive synaptic weights due to device-to-device (D2D) and cycle-to-cycle (C2C) variations is considered. Different levels of Gaussian noise are added to the memristive model during each adjustment. Another method of using memristors with binary states to build M-QNNs is presented, which suffers from fewer D2D and C2C variations compared with using multilevel memristors. Furthermore, methods of solving the sneak path issues in the memristive crossbar arrays are proposed. The M-QNN approach is evaluated on two image classification datasets, that is, ten-digit number and handwritten images of mixed National Institute of Standards and Technology (MNIST). In addition, input images with different levels of zero-mean Gaussian noise are tested to verify the robustness of the proposed method. Another highlight of the proposed method is that it can significantly reduce computational time and memory during the process of image recognition.

Quasisynchronization of Discrete-Time Inertial Neural Networks With Parameter Mismatches and Delays

Contrary to many existing works based on the continuous-time inertial neural network, this article considers the quasisynchronization issue for the discrete-time inertial neural network. To obtain the main results, we adopt the generalized matrix-measure concept. A condition ensuring the quasisynchronization is attained at first. To make the result less conservative, further analysis based on the generalized matrix measure is proceeded. An example is given to demonstrate the validity and effectiveness of the main results.

Exponential Stabilization of Inertial Memristive Neural Networks With Multiple Time Delays

This article investigates the global exponential stabilization (GES) of inertial memristive neural networks with discrete and distributed time-varying delays (DIMNNs). By introducing the inertial term into memristive neural networks (MNNs), DIMNNs are formulated as the second-order differential equations with discontinuous right-hand sides. Via a variable transformation, the initial DIMNNs are rewritten as the first-order differential equations. By exploiting the theories of differential inclusion, inequality techniques, and the comparison strategy, the p th moment GES ( p ≥ 1 ) of the addressed DIMNNs is presented in terms of algebraic inequalities within the sense of Filippov, which enriches and extends some published results. In addition, the global exponential stability of MNNs is also performed in the form of an M-matrix, which contains some existing ones as special cases. Finally, two simulations are carried out to validate the correctness of the theories, and an application is developed in pseudorandom number generation.

Intermittent Control for Quasisynchronization of Delayed Discrete-Time Neural Networks

This article visits the intermittent quasisynchronization control of delayed discrete-time neural networks (DNNs). First, an event-dependent intermittent mechanism is originally designed, which is described by the Lyapunov function and three non-negative real regions. The distinctive feature is that the controller starts to work only when the trajectory of the Lyapunov function goes into the presupposed work region. The proposed method fundamentally changes the principle of the existing intermittent control schemes. Under the proposed framework of the intermittent mechanism, the work/rest time of the controller is aperiodic, unpredictable, and initial value dependent. Second, several succinct sufficient conditions in terms of linear matrix inequalities are developed to achieve the quasisynchronization of the considered DNNs. A simple optimization algorithm is established to compute the control gains and the Lyapunov matrices such that synchronization error is stabilized to the smallest convergence region. Finally, two simulation examples are provided to demonstrate the feasibility of the designed intermittent mechanism.

Intermittent Discrete Observation Control for Synchronization of Stochastic Neural Networks

In this paper, to investigate the exponential synchronization of stochastic neural networks, a new periodically intermittent discrete observation control (PIDOC) is first proposed. Different from the existing periodically intermittent control, our control in control time is feedback control based on discrete-time state observations (FCDSOs) instead of a continuous-time one. By employing the Lyapunov method, graph theory, and theory of differential inclusions, the exponential synchronization of stochastic neural networks with a discontinuous right-hand side is realized by PIDOC and some sufficient conditions are presented. Especially, when control width tends to control period, PIDOC will be reduced to a general FCDSO and we give some detailed discussions. Then, we provide some corollaries about synchronization in mean square, asymptotical synchronization in mean square, and exponential synchronization of stochastic neural networks under FCDSO. Finally, some numerical simulations are provided to demonstrate our analytical results.