Search

This paper examines a three-dimensional delayed discrete neural network model analytically and numerically to determine the existence of different types of bifurcations of the involved fixed points. The model exhibits different bifurcations such as pitchforks, flips, Neimark–Sackers, and flip-Neimark–Sackers. The critical coefficients are used to determine the structure of each bifurcation. The curves are calculated and plotted for each bifurcation when the parameters are changed. Further, these bifurcations are theoretically analyzed and numerically verified. From the obtained results, we observed that by drawing the curves associated with each bifurcation, the numerical simulations are consistent with the analytical results. [ABSTRACT FROM AUTHOR]

To construct a nonlinear fractional-order neural network reflecting the complex environment of the real world, this paper considers the common factors such as uncertainties, perturbations, and delays that affect the stability of the network system. In particular, not only does the activation function include multiple time delays, but the memristive connection weights also consider transmission delays. Stemming from the characteristics of neural networks, two different types of discontinuous controllers with state information and sign functions are devised to effectuate network synchronization objectives. Combining the finite-time convergence criterion and the theory of fractional-order calculus, Mittag-Leffler synchronization conditions for fractional-order multi-delayed memristive neural networks (FMMNNs) are derived, and the upper bound of the setting time can be confirmed. Unlike previous jobs, this article focuses on applying different inequality techniques in the synchronous analysis process, rather than comparison principles to manage the multi-delay effects. In addition, this study removes the restrictive requirement that the activation function has a zero value at the switching jumps, and the discontinuous control protocol in this paper makes the networks achieve synchronization over a finite time, with some advantages in terms of the convergence speed. [ABSTRACT FROM AUTHOR]

The continuous Hopfield network (CHN) is a common recurrent neural network. The CHN tool can be used to solve a number of ranking and optimization problems, where the equilibrium states of the ordinary differential equation (ODE) related to the CHN give the solution to any given problem. Because of the non-local characteristic of the "infinite memory" effect, fractional-order (FO) systems have been proved to describe more accurately the behavior of real dynamical systems, compared to the model's ODE. In this paper, a fractional-order variant of a Hopfield neural network is introduced to solve a Quadratic Knap Sac Problem (QKSP), namely the fractional CHN (FRAC-CHN). Firstly, the system is integrated with the quadratic method for fractional-order equations whose trajectories have shown erratic paths and jumps to other basin attractions. To avoid these drawbacks, a new algorithm for obtaining an equilibrium point for a CHN is introduced in this paper, namely the optimal fractional CHN (OPT-FRAC-CHN). This is a variable time-step method that converges to a good local minima in just a few iterations. Compared with the non-variable time-stepping CHN method, the optimal time-stepping CHN method (OPT-CHN) and the FRAC-CHN method, the OPT-FRAC-CHN method, produce the best local minima for random CHN instances and for the optimal feeding problem. [ABSTRACT FROM AUTHOR]

Radio Frequency IDentification (RFID) Network Planning (RNP) is the problem of placing RFID readers in a working area where a tag is interrogated by at least one reader and at the same time satisfies some constraints such as minimum number of placed readers, minimal interference, and minimal outside coverage. The RNP optimization has been proven NP-hard; thus, natural-inspired approaches are often used to find the optimal solution. The paper proposes an energy-efficient RNP approach in which the positions of placed readers are optimized by a Hopfield network, and the energy efficiency is achieved through a placement area restriction technique. A mechanism of redundant reader elimination is also added to minimize the number of placed readers. Simulation results show that the Hopfield network-based energy-efficient RNP approach achieves the maximum tag coverage and energy efficiency by reducing interference, outside coverage, and the number of placed readers. [ABSTRACT FROM AUTHOR]

This paper investigates the impulsive stability analysis issues of discrete-time positive singular systems with time delay. First, the paper addresses the positivity problem of the system by providing sufficient conditions. Next, a new method based on state transformations is presented to derive a new delay-dependent criterion for the exponential stability of impulsive positive singular systems. Finally, the effectiveness of the proposed conditions is validated through three numerical examples. [ABSTRACT FROM AUTHOR]

The brain, an exceedingly intricate information processing system, poses a constant challenge to memory research, particularly in comprehending how it encodes, stores, and retrieves information. Cognitive psychology studies memory mechanism from behavioral experiment level and fMRI level, and neurobiology studies memory mechanism from anatomy and electrophysiology level. Current research findings are insufficient to provide a comprehensive, detailed explanation of memory processes within the brain. Numerous unknown details must be addressed to establish a complete information processingmechanismconnecting micro molecular cellular levels with macro cognitive behavioral levels. Key issues include characterizing and distributing content within biological neural networks, coexisting information with varying content, and sharing limited resources and storage capacity. Compared with the hard disk of computer mass storage, it is very clear from the polarity of magnetic particles in the bottom layer, the division of tracks and sectors in the middle layer, to the directory tree and file management system in the high layer, but the understanding of memory is not sufficient. Biological neural networks are abstracted as directed graphs, and the encoding, storage, and retrieval of information within directed graphs at the cellular level are explored. A memory computational model based on active directed graphs and node-adaptive learning is proposed. First, based on neuronal local perspectives, autonomous initiative, limited resource competition, and other neurobiological characteristics, a resource-based adaptive learning algorithm for directed graph nodes is designed. To minimize resource consumption of memory content in directed graphs, two resource-occupancy optimization strategies--lateral inhibition and path pruning--are proposed. Second, this paper introduces a novel memory mechanism grounded in graph theory, which considers connected subgraphs as the physical manifestation of memory content in directed graphs. The encoding, storage, consolidation, and retrieval of the brain's memory system correspond to specific operations such as forming subgraphs, accommodating multiple subgraphs, strengthening connections and connectivity of subgraphs, and activating subgraphs. Lastly, a series of experiments were designed to simulate cognitive processes and evaluate the performance of the directed graph model. Experimental results reveal that the proposed adaptive connectivity learning algorithm for directed graphs in this paper possesses the following four features: (1) Demonstrating distributed, self-organizing, and self-adaptive properties, the algorithm achieves global-level functions through local node interactions; (2) Enabling incremental storage and supporting continuous learning capabilities; (3) Displaying stable memory performance, it surpasses the Hopfield network in memory accuracy, capacity, and diversity, as demonstrated in experimental comparisons. Moreover, itmaintains highmemory performance with large-scale datasets; (4) Exhibiting a degree of generalization ability, the algorithm's macroscopic performance remains unaffected by the topological structure of the directed graph. Large-scale, decentralized, and node-autonomous directed graphs are suitable simulation methods. Examining storage problems within directed graphs can reveal the essence of phenomena and uncover fundamental storage rules hidden within complex neuronal mechanisms, such as synaptic plasticity, ion channels, neurotransmitters, and electrochemical activities. [ABSTRACT FROM AUTHOR]

Logical gates have been used in implementation of logic sequential and combinational circuits especially in computers, DSPs and microprocessors. They are mostly fabricated based on CMOS technology that provides a few nano-seconds of delay for each digital gate. Due to limitations in more scaling CMOS transistors and cause of short channel effects, some engineers and researchers believe that there is a huge demand for new devices and fabrication technologies to produce faster logic gates. In this paper, a new architecture for NAND gate is presented which operates based on mechanical resonance of a network of weakly coupled resonators that resonate in radio frequencies. This design is achieved by employing the associative memory property of Hopfield neural networks and the theory of weakly coupled resonators. The main advantage of the proposed design is in its capability to reach out delay times of the order of 1 nano-seconds or even less. One solution to decrease the delay time can be increasing the resonance frequency of resonators which are processing elements of resonators network. In this paper just the new idea of implementation NAND gate based on weakly coupled RF MEMS resonators is presented and evaluated. Other criteria like gate power consumption, effects of temperature, fan in, fan out and noise margin are not discussed. Regarding the rapid growth in MEMS technology, resonators with super high frequency (SHF 3–30 GHz) are now available and those with Extremely High frequency (EHF 30–300 GHz) will soon be in market which enables the presented design to achieve higher speeds. In addition, mechanical resonators are more fault tolerant than CMOS circuits when utilized in harsh environments which exposed to ionic beams or electron beam radiations. In space applications, the satellite and payload are exposed to huge bombardments of space electrons and ions beams. So, the proposed NAND gate can be a good solution for enhancing reliability of devices and systems exposed to space radiations. [ABSTRACT FROM AUTHOR]

In this paper, based on event-triggered control, the stabilisation problem of time-varying delay switched linear system with all subsystems unstable is studied. Firstly, the idea of event-triggered mechanism is introduced, and the state feedback controller is designed. Combining the discretised linear Lyapunov function method with the average dwell time technique, the stabilisation schemes for continuous switched system with unstable modes are obtained. Secondly, compared with existing results, the event-triggered mechanism scheme adopted under the current event-triggered control strategy reduces the number of system triggers, effectively saves computational resources, avoids Zeno's behaviour, and has better performance in terms of sampling frequency. Finally, the idea of event-triggered mechanism is first extended to discrete time-varying delay switched systems where all subsystems are unstable. By solving linear matrix inequalities, sufficient conditions for global exponential stability of the system are obtained. The effectiveness of this method was verified through a simulation example of a turbofan engine model. [ABSTRACT FROM AUTHOR]

Markovian jump Hopfield NNs (MJHNNs) have received considerable attention due to their potential for application in various areas. This paper deals with the issue of state estimation concerning a category of MJHNNs with discrete and distributed delays. Both time-invariant and time-variant discrete delay cases are taken into account. The objective is to design full-order state estimators such that the filtering error systems exhibit exponential stability in the mean-square sense. Two sufficient conditions on the mean-square exponential stability of MJHNNs are established utilizing augmented Lyapunov-Krasovskii functionals, the Wirtinger-based integral inequality, the Bessel-Legendre inequality, and the convex combination inequality. Then, linear matrix inequalities-based design methods for the required estimators are developed through eliminating nonlinear coupling terms. The feasibility of these linear matrix inequalities can be readily verified via available Matlab software, thus enabling numerically tractable implementation of the proposed design methods. Finally, two numerical examples with simulations are provided to demonstrate the applicability and less conservatism of the proposed stability criteria and estimators. Lastly, two numerical examples are given to demonstrate the applicability and reduced conservatism of the proposed stability criteria and estimator design methods. Future research could explore further refinement of these analysis and design results, and exporing their extention to more complex neural network models. [ABSTRACT FROM AUTHOR]

The growing utilization of neural networks has led to a heightened focus on the hardware implementation of such networks. Security concerns associated with these implementations pose a significant challenge in this regard. Among these problems, the vulnerability of these networks against side-channel attacks such as power attacks can be mentioned. This paper presents a technique to enhance the resilience of hardware implementations of neural networks, particularly Hopfield neural networks, to mitigate the risks posed by power attacks. In addition to the fact that the proposed method makes it impossible to attack the network, it also reduces the power consumption of the entire circuit by reducing the leakage currents. The simulation results demonstrate that the proposed approach also achieves about a 10% reduction in energy consumption while concurrently improving the accuracy of the implemented associative memory by 1.1%. [ABSTRACT FROM AUTHOR]

This paper centers on stochastic Hopfield neural networks with variable coefficients and infinite delay. First, we propose an integral inequality that improves and extends some existing works. Second, by employing some inequalities and stochastic analysis techniques, some suffcient conditions for ensuring pth moment generalized exponential stability are established. Our results do not necessitate the construction of a complex Lyapunov function or rely on the assumption of bounded variable coeffscients, and our results expand some existing works. At last, to illustrate the efficacy of our result, we present several simulation examples. [ABSTRACT FROM AUTHOR]

Using the Neural Networks to predict solar harvestable energy would contribute to prolonging the duration of the effective operation and thus less consumption in solar-harvesting sensor nodes. The NNs with higher prediction accuracy have the longest effective operation. Till now, the NNs that use the zenith angle function as input have been utilized with only two terms. This paper shows the advantages of using a multi-term zenith angle function on the energy management in the nodes. To this end, this paper considers two, three, and four terms for the function of the zenith angle. The results showed that the case of four terms has the lowest prediction mistakes on average (0.83%) compared to (2.13% and 1.75%) for the cases of two and three terms, respectively. This is followed by a reduction in energy consumption in favor of four terms case. For one month simulation period with hourly prediction, the sensor node worked at the higher consumption mode (M2) in the case of four terms 4 hours less than three terms and 7 hours less than two terms case. Thus, increasing the number of terms in the zenith angle function leads to higher accuracy and less energy consumption. [ABSTRACT FROM AUTHOR]

The activation function is crucial in the Hopfield neural network (HNN) to restrict the input–output relation of each neuron. The physical realizability and simplicity of the hardware circuit of activation function are beneficial to promote the practical engineering application of the HNN. However, the HNN commonly used hyperbolic tangent activation function involves a complex hardware circuit implementation. This paper discusses a piecewise-linear activation function (PWL-AF) with simplified circuit implementation and a tri-neuron small-world HNN is built as a paradigm. The hardware implementation circuit of the HNN is greatly simplified, benefited from the PWL-AF with a simple analog circuit. Meanwhile, the dynamics related to the PWL-AF and initial conditions are numerically explored. The numerical results demonstrate that the PWL-AF-based HNN can produce dynamical behaviors like the HNN based on the hyperbolic tangent activation function. Nevertheless, the multistability with up to six kinds of coexisting multiple attractors emerged because of the PWL-AF breakpoint. This can give more flexible and potential aspects in multistability-based engineering applications. Especially, the PWL-AF breakpoint value simultaneously acts as the offset booster and amplitude controller in regulating the offset boosting and amplitude rescaling of neuron states. Afterwards, an analog circuit with three straightforward operational amplifiers (op-amp)-based circuit modules is designed for the PWL-AF, and a PCB-based analog circuit is thereby implemented for the tri-neuron small-world HNN. The hardware experiments agree with the numerical simulations, implying the feasibility of the PWL-AF simplification for the HNN. [ABSTRACT FROM AUTHOR]

Robust stability properties of continuous-time dynamical neural networks involving time delay parameters have been extensively studied, and many sufficient criteria for robust stability of various classes of delayed dynamical neural networks have been obtained in the past literature. The class of activation functions and the types of delay terms involved in the mathematical models of dynamical neural networks are two main parameters in the determination of stability conditions for these neural network models. In this article, we will analyse a neural network model of relatively having a more complicated mathematical form where the neural system has the multiple time delay terms and the activation functions satisfy the Lipschitz conditions. By deriving a new and alternative upper bound value for the l 2 -norm of uncertain intervalised matrices and constructing some various forms of the same type of a Lyapunov functional, this paper will first propose new results on global robust stability of dynamical Hopfield neural networks having multiple time delay terms in the presence of the Lipschitz activation functions. Then, we show that some simple modified changes in robust stability conditions proposed for multiple delayed Hopfield neural network model directly yield robust stability conditions of multiple delayed Cohen-Grossberg neural network model. We will also make a very detailed review of the previously published robust stability research results, which are basically in the nonsingular M-matrix or various algebraic inequalities forms. In particular, the robust stability results proposed in this paper are proved to generalize almost all previously reported robust stability conditions for multiple delayed neural network models. Some concluding remarks and future works regarding robust stability analysis of dynamical neural systems are addressed. [ABSTRACT FROM AUTHOR]

This paper studies the input-to-state stability (ISS) and uniform stability for impulsive nonlinear systems with delayed impulses, where delays are flexible between two consecutive impulsive instants. Illustrating effects caused by delays, concepts of generalised average impulsive delay and generalised reverse average impulsive delay are introduced, and more applicable in practice. Moreover, sufficient conditions for stability properties are formulated with destabilising and stabilising impulses through a general candidate ISS-Lyapunov function and the generalised conditions. It is shown that the double effects of delays in impulses (i.e. stabilising an initial unstable system, or contrarily, destabilising an initial stable system) coincide with the existing results using the exponential candidate ISS-Lyapunov function. Finally, two examples are provided to demonstrate our developed techniques. [ABSTRACT FROM AUTHOR]

In this paper, a mathematical model for a solid spherically symmetric vascular tumor growth with nutrient periodic supply and time delays is studied. Compared to the apoptosis process of tumor cells, there is a time delay in the process of tumor cell division. The cells inside the tumor obtain nutrient σ(r,t) through blood vessels, and the tumor attracts blood vessels at a rate proportional to α(t). So, the boundary value condition ∂σ ∂r + α(t)(σ − ψ(t)) = 0,r = R(t),t > 0, holds on the boundary, where the function ψ(t) is the concentration of nutrient externally supplied to the tumor. Considering that the nutrients provided by the outside world are often periodic, the research in this paper assumes that ψ(t) is a periodic function. Sufficient conditions for the global stability of zero steady state are presented. Under certain conditions, we prove that there exists at least one periodic solution to the model. The results are illustrated by computer simulations. [ABSTRACT FROM AUTHOR]

Economic growth is resulting in serious environmental problems. Effectively establishing an economic growth model that considers environmental pollution is an important topic. To analyze the interplay between economic growth and environmental pollution, a fractional-order time-delayed economic growth model with environmental purification is proposed in this paper. The established model considers not only the environment and economic production but also the labor force population and total factor productivity. Furthermore, the asymptotic stability conditions and parameter stability interval are provided. Finally, in numerical experiments, the correctness of the theory is verified. [ABSTRACT FROM AUTHOR]

In this paper, a dynamic HIV model with cell-to-cell transmission, two immune responses, and induced apoptosis is proposed and studied. First, the non-negativity and boundedness of the solutions of the model are given, and then the exact expression of the basic reproduction number R0 is obtained by using the next generation matrix method. Second, criteria are obtained for the local stability of the disease-free equilibrium, immune response-free equilibrium, and the infected equilibrium with both humoral and cellular immune responses. Furthermore, the threshold conditions are also derived for the global asymptotic stability of the disease-free equilibrium, immune responsefree equilibrium, and the infected equilibrium with both humoral and cellular immune responses by constructing the suitable Lyapunov function. Finally, some numerical simulations are conducted to verify the theoretical results; the numerical simulation results show that the increase of apoptosis rate had a positive role in the control of viral infection. [ABSTRACT FROM AUTHOR]

This paper proposes a new H ∞ static output feedback control method to address the congestion control problem in transmission control protocol networks using active queue management routers. Based on linear matrix inequality optimization, this method determines a static output feedback control law to minimize the H ∞ norm of the transfer function between the controlled queue length of the buffer and the exogenous disturbance affecting the available link bandwidth. A linear matrix inequality formulation is presented as a sufficient condition to guarantee the closed-loop system's asymptotic stability while maintaining disturbance rejection within a specified level, regardless of round-trip time delays. The proposed robust static output feedback control eliminates the need to measure or estimate all system states, thus simplifying practical implementation. The effectiveness of the proposed design method is demonstrated by applying it in a practical process, as illustrated through a numerical example. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to study the dynamics of Hopfield neural networks with impulsive effects, focusing on Poisson stable rates, synaptic connections, and unpredictable external inputs. Through the symmetry of impulsive and differential compartments of the model, we follow and extend the principal dynamical ideas of the founder. Specifically, the research delves into the phenomena of unpredictability and Poisson stability, which have been examined in previous studies relating to models of continuous and discontinuous neural networks with constant components. We extend the analysis to discontinuous models characterized by variable impulsive actions and structural ingredients. The method of included intervals based on the B-topology is employed to investigate the networks. It is a novel approach that addresses the unique challenges posed by the sophisticated recurrence. [ABSTRACT FROM AUTHOR]

This paper is devoted to dealing with the issue of the estimation of the domain of attraction (DOA) for highly nonlinear neutral complex networks (HNNCNs) with time delays. Firstly, by the Razumikhin approach, we establish several novel lemmas on the estimation of DOA for highly nonlinear neutral differential systems. The cases of bounded non-differentiable delays and unbounded proportional delays are discussed, respectively. Subsequently, by utilizing the proposed lemmas, combining the Lyapunov stability theory and inequality technique, the estimation of DOA on HNNCNs with bounded delays or proportional delays is derived when the chosen control gain is sufficiently large. If initial values start from DOA, then the states of systems will exponentially or polynomially converge to the equilibrium point, which means that the local exponential or polynomial synchronization of HNNCNs is realized. Additionally, the weighted outer-coupling matrix of complex networks is not required to be symmetric, which means that the derived results can be applied to both the undirected networks and directed networks. Finally, several numerical examples are provided to illustrate the feasibility of theoretical findings. [ABSTRACT FROM AUTHOR]

The object of this study is the assessment of the level of enterprise bankruptcy risk. It is a critical component in assessing the financial condition of an enterprise, and also serves as an indicator that allows the management team to reduce potential risks and develop their own strategies to strengthen the financial condition of the enterprise. One of the most challenging aspects of bankruptcy forecasting is the complex financial situations of bankrupt companies. By accurately predicting the risk of bankruptcy, businesses can take preventive measures to mitigate financial difficulties and ensure long-term sustainability. Previous methods, such as Altman’s Z-score, are not accurate enough, as presented in the study. The paper investigates a modern approach to bankruptcy prediction based on a neural network with complex neural elements, namely neural arithmetic logic units (NALUs) and a custom phasing layer. This layer can process complex raw numerical values, such as financial indicators relevant to the analysis of a company’s bankruptcy. Compared to Altman’s Z-score, the developed method demonstrates a better F1 score in bankruptcy classification (48 %). On the raw data, the neural network demonstrates an improvement in the F1 score by about 40 % compared to the classical multilayer perceptron (MLP) with linear layers and nonlinear activation functions. A modern replacement for ReLU called Mish was used, which achieves better generalization. It was also assumed that the addition of new neural elements, which provide the neural network with arithmetic capabilities, contributes to the performance of processing non-normalized input data. This work highlights the importance of using advanced neural network architectures to improve the accuracy and reliability of forecasting in financial risk assessment. Using the parameters presented in the study, managers of enterprises will be able to more accurately assess the risk of bankruptcy. [ABSTRACT FROM AUTHOR]

This paper tries to study the problem of finite-time synchronization for delayed semi-Markov reaction–diffusion systems. Based on the spatial and parametric characteristics of the considered systems, a new asynchronous boundary control scheme is proposed to ensure the finite-time synchronization of the drive and response systems. In the asynchronous boundary control scheme, only an actuator should be placed at the spatial boundary, which is more easier to implement and economical than the other non-boundary control strategies. Besides, the system parameters and controller follow two asynchronous semi-Markov chains for jumping, which is more practical than obeying one semi-Markov chain. Moreover, for the considered systems, we proposes a new lemma of finite-time stability, and by employing the inequality methods and variable substitution, we derive the criterion of finite-time synchronization and a correlative corollary. Finally, a numerical example and an application example on secure communication are carried out to support the developed approach. • Our study enriches the related research of semi-Markov RDSs. The obtained results guarantee the finite-time synchronization of semi-Markov RDSs, which is more effective and practical than asymptotic synchronization. • This paper proposes a novel asynchronous boundary control scheme, for the synchronization of semi-Markov RDSs. Compared with existing ones, our control scheme has obvious advantages in realizability and economy. • Based on the existing papers, in the designed controller, a constant is introduced, such that the intense chatter of controller could be reduced. • For the considered systems and designed controller, a new finite-time stability lemma is proposed, which enables the derivation of a finite-time synchronization criterion and a related corollary of this paper. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

An important difference between brains and deep neural networks is the way they learn. Nervous systems learn online where a stream of noisy data points are presented in a non-independent, identically distributed way. Further, synaptic plasticity in the brain depends only on information local to synapses. Deep networks, on the other hand, typically use non-local learning algorithms and are trained in an offline, non-noisy, independent, identically distributed setting. Understanding how neural networks learn under the same constraints as the brain is an open problem for neuroscience and neuromorphic computing. A standard approach to this problem has yet to be established. In this paper, we propose that discrete graphical models that learn via an online maximum a posteriori learning algorithm could provide such an approach. We implement this kind of model in a neural network called the Sparse Quantized Hopfield Network. We show our model outperforms state-of-the-art neural networks on associative memory tasks, outperforms these networks in online, continual settings, learns efficiently with noisy inputs, and is better than baselines on an episodic memory task. Brains and neuromorphic systems learn with local learning rules in online-continual learning scenarios. Designing neural networks that learn effectively under these conditions is challenging. The authors introduce a neural network that implements an effective, principled approach to local, online-continual learning on associative memory tasks. [ABSTRACT FROM AUTHOR]

The electro-hydraulic servo system has advantages such as high pressure, large flow, and high power, etc., which can also realize stepless regulation, so it is widely used in many engineering machineries. A linear model is sometimes only a simple approximation of an idealized model, but in an actual system, there may be nonlinear and transient variation characteristics in the systems. Coupling is reflected in the fact that the components or functional structures implemented by each system used for the design of hydraulic systems are not completely or independently related to each other, but affect each other. The nonlinear clearance between the actuator and the load reduces the control accuracy of the system and increases the impact, thus losing stable working conditions. In the paper, based on the nonlinear clearance problem of the electro-hydraulic servo system, a mathematical transfer model with clearance is established, and on this basis, a clearance compensation method based on the Hopfield neural network is proposed. In this way, clearance compensation can be realized by adjusting the parameters of neural network nodes, through simple and convenient operation. Finally, by setting different clearance values, the results of the step response and sine response curve before and after clearance compensation of the hydraulic system are compared, and the effectiveness of Hopfield neural network compensation clearance control is verified based on the comparison simulation results. [ABSTRACT FROM AUTHOR]

Linear assignment problems hold a pivotal role in combinatorial optimization, offering a broad spectrum of applications within the field of data sciences. They consist of assigning "agents" to "tasks" in a way that leads to a minimum total cost associated with the assignment. The assignment is balanced when the number of agents equals the number of tasks, with a one-to-one correspondence between agents and tasks, and it is and unbalanced otherwise. Additional options and constraints may be imposed, such as allowing agents to perform multiple tasks or allowing tasks to be performed by multiple agents. In this paper, we propose a novel framework that can solve all these assignment problems employing methodologies derived from the field of statistical physics. We describe this formalism in detail and validate all its assertions. A major part of this framework is the definition of a concave effective free energy function that encapsulates the constraints of the assignment problem within a finite temperature context. We demonstrate that this free energy monotonically decreases as a function of a parameter β representing the inverse of temperature. As β increases, the free energy converges to the optimal assignment cost. Furthermore, we demonstrate that when β values are sufficiently large, the exact solution to the assignment problem can be derived by rounding off the elements of the computed assignment matrix to the nearest integer. We describe a computer implementation of our framework and illustrate its application to multi-task assignment problems for which the Hungarian algorithm is not applicable. [ABSTRACT FROM AUTHOR]

Memristor is a kind of nonlinear resistance with memory function, which is a typical nonlinear circuit component. In this paper, the problem of a simple chaotic circuit based on the memristor was studied. We constructed a new simple circuit of multiple memorizing components, summarized the mathematical model and found seven types of chaotic attractors without reference to classical circuits that substituted memristors for elements in the original circuit. Traditional methods of dynamic analysis are used to analyze the equilibrium point and stability of the system. Furthermore, we analyzed the dynamical behavior with the varying coefficient of the system specifically. In order to reduce the deviation from the actual physical circuit system as much as possible so as to facilitate the follow-up research of scholars, we solved the problem of Hopf bifurcation in this system under the condition of time delay through the use of the canonical form and Hopf bifurcation theory. Theoretical analysis and simulation results show that there existed the state transition in seven chaotic attractors of system and the bifurcation was stable when we changed the parameter τ slightly. As a small unit circuit, this paper lays a foundation for the research and control of large-scale system with memorizing components. [ABSTRACT FROM AUTHOR]

This paper investigates how to solve image classification with Hopfield neural networks (HNNs) and oscillatory neural networks (ONNs). This is a first attempt to apply ONNs for image classification. State-of-the-art image classification networks are multi-layer models trained with supervised gradient back-propagation, which provide high-fidelity results but require high energy consumption and computational resources to be implemented. On the contrary, HNN and ONN networks are single-layer, requiring less computational resources, however, they necessitate some adaptation as they are not directly applicable for image classification. ONN is a novel brain-inspired computing paradigm that performs low-power computation and is attractive for edge artificial intelligence applications, such as image classification. In this paper, we perform image classification with HNN and ONN by exploiting their auto-associative memory (AAM) properties. We evaluate precision of HNN and ONN trained with state-of-the-art unsupervised learning algorithms. Additionally, we adapt the supervised equilibrium propagation (EP) algorithm to single-layer AAM architectures, proposing the AAM-EP. We test and validate HNN and ONN classification on images of handwritten digits using a simplified MNIST set. We find that using unsupervised learning, HNN reaches 65.2%, and ONN 59.1% precision. Moreover, we show that AAM-EP can increase HNN and ONN precision up to 67.04% for HNN and 62.6% for ONN. While intrinsically HNN and ONN are not meant for classification tasks, to the best of our knowledge, these are the best-reported precisions of HNN and ONN performing classification of images of handwritten digits. [ABSTRACT FROM AUTHOR]

The security of mobile wireless sensor networks has captivated extensive attention of researchers because of their wide range of applications and vulnerability to attacks caused by malware. In this paper, we investigate a delayed malware propagation model on mobile wireless sensor network incorporating nonlinear incidence rate, logistic growth rate and recovery rate. Local asymptotic stability of the endemic equilibrium and existence of Hopf bifurcation at crucial value of the time delay are analyzed. Then, properties of Hopf bifurcation are explored. Specifically, global exponential stability is investigated via linear matrix inequality. An example is presented finally to underline the effectiveness of findings in our paper numerically and graphically. [ABSTRACT FROM AUTHOR]

In this paper, we study the problem of attitude trajectory tracking of rigid bodies subject to external disturbances. The attitude control problem has been studied in the last decades and novel solutions have been proposed. Nevertheless, most of the proposed controllers only achieve local or almost global asymptotic stability without considering external disturbances. Contrary to other works, we focus on the problem of achieving almost global exponential stability of the attitude tracking errors in the presence of external disturbances using continuous control laws. We propose an attitude trajectory tracking controller based on the exponential coordinates of rotation in combination with a disturbance observer that estimates the exogenous signals. To solve this problem, we adopt a hierarchical approach, where the proposed control law is divided into a kinematic controller (outer control loop) and a velocity tracking controller (inner control loop). To design the disturbance observer, it is assumed that exogenous signals can be generated by a linear exosystem, i.e. the magnitude and phase of the disturbance are unknown. The almost global exponential stability of the closed-loop dynamics' equilibrium point was proved by a strict Lyapunov function. The performance of the proposed approach is assessed by numerical simulations and experimental tests on a low-cost quadrotor. [ABSTRACT FROM AUTHOR]

This paper is concerned with reset controller design and $ \mathcal {L}_2 $ L 2 -gain stability of piecewise-affine systems under the framework of hybrid systems. Firstly, stability conditions of piecewise-affine systems under dynamic state-feedback control are established through bilinear matrix inequality conditions. Secondly, a reset controller with reset rules under the hybrid systems framework is proposed in the sense of Lyapunov and sufficient conditions for exponential and $ \mathcal {L}_2 $ L 2 -gain stability of the closed-loop systems are provided. Different from the piecewise-affine systems with the dynamic state-feedback controller, the reset controller is designed such that the $ \mathcal {L}_2 $ L 2 -gain performance of piecewise-affine systems can be enhanced. Thirdly, an LMI approach is proposed to avoid the difficulty of solving the bilinear matrix inequalities. Furthermore, robustness to inflations of the flow and jump sets is established, and robustness to the norm-bounded uncertainties is proposed. Finally, numerical simulations including a robot arm system, an inverted pendulum system and the Chua's circuit system are provided to illustrate the results. [ABSTRACT FROM AUTHOR]

To reduce the communication and computation overhead of neural networks, a novel pinning event-triggered scheme (PETS) is developed in this paper, which enables pinning synchronization of uncertain coupled memristive neural networks (CMNNs) under limited resources. Time-varying delays, uncertainties, and mismatched parameters are all considered, which makes the system more interpretable. In addition, from the low energy cost point of view, an algorithm for pinned node selection is designed to further investigate the newly event-triggered function under limited communication resources. Meanwhile, based on the PETS and following the Lyapunov functional method, sufficient conditions for the pinning exponential stability of the proposed coupled error system are formulated, and the analysis of the self-triggered method shows that our method can efficiently avoid Zeno behavior under the newly determined triggered conditions, which contribute to better PETS performance. Extensive experiments demonstrate that the PETS significantly outperforms the existing schemes in terms of solution quality. [ABSTRACT FROM AUTHOR]

Testing modern integrated circuit (IC) is challenging with introduction of System-on Chip (SOC). Enormous test pattern count is required to authenticate the IC which inflates power consumption. Henceforth, it is mandatory to incorporate power minimization techniques at circuit design phase. Optimizing test patterns is one such effective technique that curtails test power without altering circuit design. In this paper, a new test pattern reordering algorithm is proposed based on Recurrent Neural Network. Hopfield Neural Network (HNN) constitutes an optimized solution for solving traveling salesman problem (TSP). Since, test pattern reordering can be interpreted as TSP, optimized test pattern order is attained with HNN. Energy function of this algorithm falls into local minimum, so to eradicate this issue, the algorithm is modified. Test patterns are reordered with minimal hamming distance among consecutive test patterns. The proposed algorithm is implemented in ISCAS'89 Sequential Benchmark circuits. Experimental results prove that significant reduction in transition count is accomplished with proposed algorithm without compromising fault coverage. [ABSTRACT FROM AUTHOR]

Combinatorial optimization problems are ubiquitous and computationally hard to solve in general. Quantum approximate optimization algorithm (QAOA), one of the most representative quantum-classical hybrid algorithms, is designed to solve combinatorial optimization problems by transforming the discrete optimization problem into a classical optimization problem over continuous circuit parameters. QAOA objective landscape is notorious for pervasive local minima, and its viability significantly relies on the efficacy of the classical optimizer. In this work, we design double adaptive-region Bayesian optimization (DARBO) for QAOA. Our numerical results demonstrate that the algorithm greatly outperforms conventional optimizers in terms of speed, accuracy, and stability. We also address the issues of measurement efficiency and the suppression of quantum noise by conducting the full optimization loop on a superconducting quantum processor as a proof of concept. This work helps to unlock the full power of QAOA and paves the way toward achieving quantum advantage in practical classical tasks. There is no universal way of optimizing the variation quantum circuits used in Noisy Intermediate-Scale Quantum (NISQ) applications. In this paper the authors introduce a new classical Bayesian optimizer, which converges much more quickly than conventional approaches, and test it for solving the Quantum Approximate Optimization Algorithm (QAOA) problem. [ABSTRACT FROM AUTHOR]

This paper studies the stability criterion and controller design for time-delay switched systems with input saturation. The main contributions of this paper are as follows: (1) Based on constructing the Lyapunov–Krasovskii functional (LKF) with the triple integral term and making full use of the delay lower bound information, the sufficient conditions for the exponential stability of the system are given. (2) A state feedback controller is designed for the input-saturated system. (3) The symmetric delay rate problem is considered to accurately define the derivative of LKF, which reduces the conservatism of the system. By reducing conservatism, that is, the time-delay upper bound is raised, allowing for a wider range of time-delay signals. Finally, the effectiveness of the proposed method is verified by the numerical examples. [ABSTRACT FROM AUTHOR]

Efficient integration of wind energy requires accurate wind power forecasting. This prediction is critical in optimising grid operation, energy trading, and effectively harnessing renewable resources. However, the wind's complex and variable nature poses considerable challenges to achieving accurate forecasts. In this context, the accuracy of wind parameter forecasts, including wind speed and direction, is essential to enhancing the precision of wind power predictions. The presence of missing data in these parameters further complicates the forecasting process. These missing values could result from sensor malfunctions, communication issues, or other technical constraints. Addressing this issue is essential to ensuring the reliability of wind power predictions and the stability of the power grid. This paper proposes a long short-term memory (LSTM) model to forecast missing wind speed and direction data to tackle these issues. A fractional-order neural network (FONN) with a fractional arctan activation function is also developed to enhance generated wind power prediction. The predictive efficacy of the FONN model is demonstrated through two comprehensive case studies. In the first case, wind direction and forecast wind speed data are used, while in the second case, wind speed and forecast wind direction data are used for predicting power. The proposed hybrid neural network model improves wind power forecasting accuracy and addresses data gaps. The model's performance is measured using mean errors and R2 values. [ABSTRACT FROM AUTHOR]

In this paper, event-triggered control for uncertain delayed neural networks (DNNs) with actuator saturation against deception attack is discussed. We propose a novel framework into which an event-triggered mechanism (ETM), actuator saturation, system uncertainty, and deception attack are combined. In the framework, the discrete ETM is employed to determine whether the sampled signal should be transmitted to controller so as to save network bandwidth, a random occurrence deception attack model satisfying Bernoulli distribution is introduced to construct the system robust, and actuator saturation is considered due to the actual complex network environment. Based on the framework, we discussed the stochastic stability of a novel delayed neural network model in a closed-loop system. By resorting to the appropriate Lyapunov–Krasovskii functional (LKF), we derive some new sufficient conditions for the stochastically stable of the system and obtain the gain of the system controller using efficient linear matrix inequality (LMI) method. Finally, a numerical example, in the end, demonstrates the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

This paper is concerned with the finite-time annular domain stability and stabilisation for the positive systems. A new analysis method is proposed to obtain less conservative finite-time annular domain stability criteria and its superiority to modified Gronwall inequality is analysed. Moreover, conditions for the existence of state feedback and observer-based controllers that guarantee the closed-loop system to be positive and finite-time annular domain stable are given under the linear programming framework. Finally, two numerical examples are provided to show the effectiveness and superiority of the theoretical results. [ABSTRACT FROM AUTHOR]

Purpose: This paper aims to study a neural network-based fault-tolerant controller to improve the tracking control performance of an unmanned autonomous helicopter with system uncertainty, external disturbances and sensor faults, using the prescribed performance method. Design/methodology/approach: To ensure that the tracking error satisfies the prescribed performance, the authors adopt an error transformation function method. A control scheme based on the neural network and high-order disturbance observer is designed to guarantee the boundedness of the closed-loop system. A simulation is performed to prove the validity of the control scheme. Findings: The developed adaptive fault-tolerant control method makes the system with sensor fault realize tracking control. The error transformation function method can effectively handle the prescribed performance requirements. Sensor fault can be regarded as a type of system uncertainty. The uncertainty can be approximated accurately using neural networks. A high-order disturbance observer can effectively suppress compound disturbances. Originality/value: The tracking performance requirements of unmanned autonomous helicopter system are considered in the design of sensor fault-tolerant control. The inequality constraint that the output tracking error must satisfy is transformed into an unconstrained problem by introducing an error transformation function. The fault state of the velocity sensor is considered as the system uncertainty, and a neural network is used to approach the total uncertainty. Neural network estimation errors and external disturbances are treated as compound disturbances, and a high-order disturbance observer is constructed to compensate for them. [ABSTRACT FROM AUTHOR]

The current development of logic satisfiability in discrete Hopfield neural networks (DHNN)has been segregated into systematic logic and non-systematic logic. Most of the research tends to improve non-systematic logical rules to various extents, such as introducing the ratio of a negative literal and a flexible hybrid logical structure that combines systematic and non-systematic structures. However, the existing non-systematic logical rule exhibited a drawback concerning the impact of negative literal within the logical structure. Therefore, this paper presented a novel class of non-systematic logic called conditional random k satisfiability for k=1,2 while intentionally disregarding both positive literals in second-order clauses. The proposed logic was embedded into the discrete Hopfield neural network with the ultimate goal of minimizing the cost function. Moreover, a novel non-monotonic Smish activation function has been introduced with the aim of enhancing the quality of the final neuronal state. The performance of the proposed logic with new activation function was compared with other state of the art logical rules in conjunction with five different types of activation functions. Based on the findings, the proposed logic has obtained a lower learning error, with the highest total neuron variation TV=857 and lowest average of Jaccard index, JSI=0.5802. On top of that, the Smish activation function highlights its capability in the DHNN based on the result ratio of improvement Zm and TV. The ratio of improvement for Smish is consistently the highest throughout all the types of activation function, showing that Smish outperforms other types of activation functions in terms of Zm and TV. This new development of logical rule with the non-monotonic Smish activation function presents an alternative strategy to the logic mining technique. This finding will be of particular interest especially to the research areas of artificial neural network, logic satisfiability in DHNN and activation function. [ABSTRACT FROM AUTHOR]

With the rapid development of the Internet era and the high popularity of computers, China's economy, politics, and culture have made rapid progress in recent years. In order to adapt to this era of rapid change, China's higher education has also undergone great changes and carried out reform and innovation. As the top priority in the Internet era, computers should be reformed first. The traditional education model is mainly teacher-centered and classroom-centered. The disadvantages of this teaching mode are that students' subjective initiative cannot be fully developed and brought into play. Traditional teaching pays attention to knowledge teaching and ignores ability training. It emphasizes speaking and neglects practice. Therefore, in order to meet the development needs of the new era and cultivate modern talents, colleges and universities began to explore the innovation and entrepreneurship education mode. There is an application of TRIZ theory to the cultivation of innovation and entrepreneurship education, and TRIZ theory is a theory for solving invention problems. Its main content is to find its own laws in the process of technological evolution and analyze the laws to get a general solution, but there are many obstacles in exploring the mode of innovation and entrepreneurship education; for example, many governments do not support this education reform and do not broadcast relevant education and teaching funds for schools, resulting in uneven configuration of software and hardware in schools. According to the survey, the proportion of innovation and entrepreneurship education in the eastern coastal areas is as high as 70%, while the proportion of innovation and entrepreneurship education in the central and western regions is only 10%. This set of data shows that regional differences are the main reason for the differences in education development. In terms of the proportion of education funds, although the annual education funds will gradually increase in recent years, the proportion is still a drop in the bucket in front of huge fiscal revenue, with the highest being only 0.1%. Therefore, in order to improve the current situation of innovation and entrepreneurship education mode in colleges and universities, according to their own characteristics, the reform is carried out from the aspects of practical ability, competition participation, and training plan, and the BP neural network model is introduced to predict and analyze the effect of teaching methods. The results of this paper are investigated and analyzed. Finally, the investigation on the development of KAB course and SYB course and the analysis on the stability and error of BP neural network are within the allowable range, this shows that the model established in this paper is more favored by students than the traditional teaching methods, more in line with the social reality, the effect is more ideal, and the result is more stable. [ABSTRACT FROM AUTHOR]

This paper is concerned with the global asymptotic stability (GAS) problem of fixed-point Lipschitz nonlinear digital filters employing 2's complement overflow arithmetic. Nonlinear digital filtering finds immense applications in various fields such as adaptive systems and controllers, digital controllers and observers for nonlinear systems, realization of neural networks using digital hardware, controllers for feedback linearization, etc. Lipschitz nonlinear digital filter is considered in this paper as it is frequently employed in nonlinear digital filtering, state filtering, neural networks, feedback control, digital controllers, decision-taking systems and so on. Based on Lyapunov theory, the property of 2's complement overflow arithmetic and Lipschitz condition associated with system nonlinearities, a new criterion for the suppression of overflow oscillations in 2's complement state variable realizations of digital filters is established. Several examples along with simulation results are provided to highlight the utility of the criterion. [ABSTRACT FROM AUTHOR]

Based on the research of genetic algorithm (GA) to optimize the BP neural network algorithm, this paper proposes a method for predicting twisted wire crosstalk based on the algorithm. Firstly, the equivalent circuit model of a multi-conductor transmission line is established, combined with the method of similarity transformation, the second-order differential transmission line equations are decoupled into n groups of independent two-conductor transmission line equations, and the crosstalk is finally solved. Then the mathematical model of the twisted wire is established and its structural characteristics are analyzed, and the GA-BP neural network algorithm is used to realize the mapping of the electromagnetic parameter matrix of the twisted wire and the position of the twisted wire. Finally, the mapping relationship is substituted into the transmission line equation, and the near-end crosstalk (NEXT) and the farend crosstalk (FEXT) of an example three-core twisted wire are predicted based on the idea of cascade combined. By comparing with the transmission line matrix method (TLM), it can be seen that the method proposed in this paper is in good agreement with the crosstalk results obtained by the electromagnetic field numerical method, which verifies the effectiveness of the algorithm proposed in this paper. [ABSTRACT FROM AUTHOR]

For this paper, we consider the almost sure exponential stability of uncertain stochastic Hopfield neural networks based on subadditive measures. Firstly, we deduce two corollaries, using the Itô–Liu formula. Then, we introduce the concept of almost sure exponential stability for uncertain stochastic Hopfield neural networks. Next, we investigate the almost sure exponential stability of uncertain stochastic Hopfield neural networks, using the Lyapunov method, Liu inequality, the Liu lemma, and exponential martingale inequality. In addition, we prove two sufficient conditions for almost sure exponential stability. Furthermore, we consider stabilization with linear uncertain stochastic perturbation and present some exceptional examples. Finally, our paper provides our conclusion. [ABSTRACT FROM AUTHOR]

In this paper, the problem on finite-/fixed-time synchronization (FFTS) is investigated for a class of diffusive Hopfield neural networks with leakage and discrete delays. Some new and useful criteria independent on time delays but dependent on the diffusion coefficients are established to guarantee the FFTS for the addressed network model under a unified framework. In sharp contrast to the existed results which can only finite-timely or fixed-timely synchronize the systems with both diffusion effects and leakage delays, the theoretical results of this paper are more general and practical. Finally, a numerical example is presented to show the effectiveness of the proposed control methods. [ABSTRACT FROM AUTHOR]

In this paper, the existence, uniqueness and global exponential stability of pseudo almost periodic solutions for a class of octonion-valued neutral type high-order Hopfield neural network models with D operator are established by using the Banach fixed point theorem and differential inequality techniques. Compared with most existing models, in this class of networks, all connection weights and activation functions are assumed to be octonion-valued functions except for time delays. And unlike most of the existing methods of studying octonion-valued neural networks, our method is a non-decomposition method, that is, the method of directly studying octonion-valued systems. The results and methods in this paper are new. In addition, an example and its numerical simulation are given to illustrate the feasibility of our results. [ABSTRACT FROM AUTHOR]

In this paper, we aim to establish the uniform stability criteria for fractional‐order time‐delayed gene regulatory networks with leakage delays (FOTDGRNL). First, we establish the existence and uniqueness of the considered systems by using the Banach fixed point theorem. Second, the delay‐dependent uniform stability and robust uniform stability of FOFGRNLT are investigated with the help of certain analysis techniques depending on equivalent norm techniques. Finally, the paper comes up with two numerical examples to justify the applicability of our theoretical results. [ABSTRACT FROM AUTHOR]