Physics informed neural networks(PINNs)are a deep learning approach designed to solve partial differential equations(PDEs).Accurately learning the initial conditions is crucial when employing PINNs to solve PDEs.Howev...Physics informed neural networks(PINNs)are a deep learning approach designed to solve partial differential equations(PDEs).Accurately learning the initial conditions is crucial when employing PINNs to solve PDEs.However,simply adjusting weights and imposing hard constraints may not always lead to better learning of the initial conditions;sometimes it even makes it difficult for the neural networks to converge.To enhance the accuracy of PINNs in learning the initial conditions,this paper proposes a novel strategy named causally enhanced initial conditions(CEICs).This strategy works by embedding a new loss in the loss function:the loss is constructed by the derivative of the initial condition and the derivative of the neural network at the initial condition.Furthermore,to respect the causality in learning the derivative,a novel causality coefficient is introduced for the training when selecting multiple derivatives.Additionally,because CEICs can provide more accurate pseudo-labels in the first subdomain,they are compatible with the temporal-marching strategy.Experimental results demonstrate that CEICs outperform hard constraints and improve the overall accuracy of pre-training PINNs.For the 1D-Korteweg–de Vries,reaction and convection equations,the CEIC method proposed in this paper reduces the relative error by at least 60%compared to the previous methods.展开更多
The single event effects(SEEs)evaluations caused by atmospheric neutrons were conducted on three different convolutional neural network(CNN)models(Yolov3,MNIST,and ResNet50)in the atmospheric neutron irradiation spect...The single event effects(SEEs)evaluations caused by atmospheric neutrons were conducted on three different convolutional neural network(CNN)models(Yolov3,MNIST,and ResNet50)in the atmospheric neutron irradiation spectrometer(ANIS)at the China Spallation Neutron Source(CSNS).The Yolov3 and MNIST models were implemented on the XILINX28-nm system-on-chip(So C).Meanwhile,the Yolov3 and ResNet50 models were deployed on the XILINX 16-nm Fin FET Ultra Scale+MPSoC.The atmospheric neutron SEEs on the tested CNN systems were comprehensively evaluated from six aspects,including chip type,network architecture,deployment methods,inference time,datasets,and the position of the anchor boxes.The various types of SEE soft errors,SEE cross-sections,and their distribution were analyzed to explore the radiation sensitivities and rules of 28-nm and 16-nm SoC.The current research can provide the technology support of radiation-resistant design of CNN system for developing and applying high-reliability,long-lifespan domestic artificial intelligence chips.展开更多
This paper addresses the issue of nonfragile state estimation for memristive recurrent neural networks with proportional delay and sensor saturations. In practical engineering, numerous unnecessary signals are transmi...This paper addresses the issue of nonfragile state estimation for memristive recurrent neural networks with proportional delay and sensor saturations. In practical engineering, numerous unnecessary signals are transmitted to the estimator through the networks, which increases the burden of communication bandwidth. A dynamic event-triggered mechanism,instead of a static event-triggered mechanism, is employed to select useful data. By constructing a meaningful Lyapunov–Krasovskii functional, a delay-dependent criterion is derived in terms of linear matrix inequalities for ensuring the global asymptotic stability of the augmented system. In the end, two numerical simulations are employed to illustrate the feasibility and validity of the proposed theoretical results.展开更多
To avoid the aerodynamic performance loss of airfoil at non-design state which often appears in single point design optimization, and to improve the adaptability to the uncertain factors in actual flight environment, ...To avoid the aerodynamic performance loss of airfoil at non-design state which often appears in single point design optimization, and to improve the adaptability to the uncertain factors in actual flight environment, a two-dimensional stochastic airfoil optimization design method based on neural networks is presented. To provide highly efficient and credible analysis, four BP neural networks are built as surrogate models to predict the airfoil aerodynamic coefficients and geometry parameter. These networks are combined with the probability density function obeying normal distribution and the genetic algorithm, thus forming an optimization design method. Using the method, for GA（W）-2 airfoil, a stochastic optimization is implemented in a two-dimensional flight area about Mach number and angle of attack. Compared with original airfoil and single point optimization design airfoil, results show that the two-dimensional stochastic method can improve the performance in a specific flight area, and increase the airfoil adaptability to the stochastic changes of multiple flight parameters.展开更多
Optical neural networks have significant advantages in terms of power consumption,parallelism,and high computing speed,which has intrigued extensive attention in both academic and engineering communities.It has been c...Optical neural networks have significant advantages in terms of power consumption,parallelism,and high computing speed,which has intrigued extensive attention in both academic and engineering communities.It has been considered as one of the powerful tools in promoting the fields of imaging processing and object recognition.However,the existing optical system architecture cannot be reconstructed to the realization of multi-functional artificial intelligence systems simultaneously.To push the development of this issue,we propose the pluggable diffractive neural networks(P-DNN),a general paradigm resorting to the cascaded metasurfaces,which can be applied to recognize various tasks by switching internal plug-ins.As the proof-of-principle,the recognition functions of six types of handwritten digits and six types of fashions are numerical simulated and experimental demonstrated at near-infrared regimes.Encouragingly,the proposed paradigm not only improves the flexibility of the optical neural networks but paves the new route for achieving high-speed,low-power and versatile artificial intelligence systems.展开更多
In this article, we consider the global chaotic synchronization of general cou- pled neural networks, in which subsystems have both discrete and distributed delays. Stochastic perturbations between subsystems are also...In this article, we consider the global chaotic synchronization of general cou- pled neural networks, in which subsystems have both discrete and distributed delays. Stochastic perturbations between subsystems are also considered. On the basis of two sim- ple adaptive pinning feedback control schemes, Lyapunov functional method, and stochas- tic analysis approach, several sufficient conditions are developed to guarantee global syn- chronization of the coupled neural networks with two kinds of delay couplings, even if only partial states of the nodes are coupled. The outer-coupling matrices may be symmetric or asymmetric. Unlike existing results that an isolate node is introduced as the pinning target, we pin to help the network realizing synchronization without introducing any iso- late node when the network is not synchronized. As a by product, sufficient conditions under which the network realizes synchronization without control are derived. Numerical simulations confirm the effectiveness of the obtained results.展开更多
In this paper, the global asymptotic stability problem of Markovian jumping stochastic Cohen-Grossberg neural networks with discrete and distributed time-varying delays （MJSCGNNs） is considered. A novel LMI-based st...In this paper, the global asymptotic stability problem of Markovian jumping stochastic Cohen-Grossberg neural networks with discrete and distributed time-varying delays （MJSCGNNs） is considered. A novel LMI-based stability criterion is obtained by constructing a new Lyapunov functional to guarantee the asymptotic stability of MJSCGNNs. Our results can be easily verified and they are also less restrictive than previously known criteria and can be applied to Cohen-Grossberg neural networks, recurrent neural networks, and cellular neural networks. Finally, the proposed stability conditions are demonstrated with numerical examples.展开更多
In a very recent study,Prof.Lingling Huang and co-workers proposed and demonstrated reconfigurable optical neural networks based on cascaded metasurfaces.By fixing one metasurface and switching the other pluggable met...In a very recent study,Prof.Lingling Huang and co-workers proposed and demonstrated reconfigurable optical neural networks based on cascaded metasurfaces.By fixing one metasurface and switching the other pluggable metasurfaces,the neural networks,which operate at near-infrared wavelengths,can perform distinct recognition tasks for handwritten digits and fashion products.This innovative device opens up an avenue for all-optical,high-speed,low-power,and multifunctional artificial intelligence systems.展开更多
We investigate the stochastic asymptotical synchronization of chaotic Markovian jumping fuzzy cellular neural networks （MJFCNNs） with discrete, unbounded distributed delays, and the Wiener process based on sampled-d...We investigate the stochastic asymptotical synchronization of chaotic Markovian jumping fuzzy cellular neural networks （MJFCNNs） with discrete, unbounded distributed delays, and the Wiener process based on sampled-data control using the linear matrix inequality （LMI） approach. The Lyapunov–Krasovskii functional combined with the input delay approach as well as the free-weighting matrix approach is employed to derive several sufficient criteria in terms of LMIs to ensure that the delayed MJFCNNs with the Wiener process is stochastic asymptotical synchronous. Restrictions （e.g., time derivative is smaller than one） are removed to obtain a proposed sampled-data controller. Finally, a numerical example is provided to demonstrate the reliability of the derived results.展开更多
Neuromorphic computing,inspired by the human brain,uses memristor devices for complex tasks.Recent studies show that self-organizing random nanowires can implement neuromorphic information processing,enabling data ana...Neuromorphic computing,inspired by the human brain,uses memristor devices for complex tasks.Recent studies show that self-organizing random nanowires can implement neuromorphic information processing,enabling data analysis.This paper presents a model based on these nanowire networks,with an improved conductance variation profile.We suggest using these networks for temporal information processing via a reservoir computing scheme and propose an efficient data encoding method using voltage pulses.The nanowire network layer generates dynamic behaviors for pulse voltages,allowing time series prediction analysis.Our experiment uses a double stochastic nanowire network architecture for processing multiple input signals,outperforming traditional reservoir computing in terms of fewer nodes,enriched dynamics and improved prediction accuracy.Experimental results confirm the high accuracy of this architecture on multiple real-time series datasets,making neuromorphic nanowire networks promising for physical implementation of reservoir computing.展开更多
High-resolution flow field data has important applications in meteorology,aerospace engineering,high-energy physics and other fields.Experiments and numerical simulations are two main ways to obtain high-resolution fl...High-resolution flow field data has important applications in meteorology,aerospace engineering,high-energy physics and other fields.Experiments and numerical simulations are two main ways to obtain high-resolution flow field data,while the high experiment cost and computing resources for simulation hinder the specificanalysis of flow field evolution.With the development of deep learning technology,convolutional neural networks areused to achieve high-resolution reconstruction of the flow field.In this paper,an ordinary convolutional neuralnetwork and a multi-time-path convolutional neural network are established for the ablative Rayleigh-Taylorinstability.These two methods can reconstruct the high-resolution flow field in just a few seconds,and further greatlyenrich the application of high-resolution reconstruction technology in fluid instability.Compared with the ordinaryconvolutional neural network,the multi-time-path convolutional neural network model has smaller error and canrestore more details of the flow field.The influence of low-resolution flow field data obtained by the two poolingmethods on the convolutional neural networks model is also discussed.展开更多
UAV-aided cellular networks,millimeter wave(mm-wave) communications and multi-antenna techniques are viewed as promising components of the solution for beyond-5G(B5G) and even 6G communications.By leveraging the power...UAV-aided cellular networks,millimeter wave(mm-wave) communications and multi-antenna techniques are viewed as promising components of the solution for beyond-5G(B5G) and even 6G communications.By leveraging the power of stochastic geometry,this paper aims at providing an effective framework for modeling and analyzing a UAV-aided heterogeneous cellular network,where the terrestrial base stations(TBSs) and the UAV base stations(UBSs) coexist,and the UBSs are provided with mm-wave and multi-antenna techniques.By modeling the TBSs as a PPP and the UBSs as a Matern hard-core point process of type Ⅱ(MPH-Ⅱ),approximated but accurate analytical results for the average rate of the typical user of both tiers are derived through an approximation method based on the mean interference-to-signal ratio(MISR) gain.The influence of some relevant parameters is discussed in detail,and some insights into the network deployment and optimization are revealed.Numerical results show that some trade-offs are worthy of being considered,such as the antenna array size,the altitude of the UAVs and the power control factor of the UBSs.展开更多
Efficiently solving partial differential equations(PDEs)is a long-standing challenge in mathematics and physics research.In recent years,the rapid development of artificial intelligence technology has brought deep lea...Efficiently solving partial differential equations(PDEs)is a long-standing challenge in mathematics and physics research.In recent years,the rapid development of artificial intelligence technology has brought deep learning-based methods to the forefront of research on numerical methods for partial differential equations.Among them,physics-informed neural networks(PINNs)are a new class of deep learning methods that show great potential in solving PDEs and predicting complex physical phenomena.In the field of nonlinear science,solitary waves and rogue waves have been important research topics.In this paper,we propose an improved PINN that enhances the physical constraints of the neural network model by adding gradient information constraints.In addition,we employ meta-learning optimization to speed up the training process.We apply the improved PINNs to the numerical simulation and prediction of solitary and rogue waves.We evaluate the accuracy of the prediction results by error analysis.The experimental results show that the improved PINNs can make more accurate predictions in less time than that of the original PINNs.展开更多
Physics-informed neural networks(PINNs)have become an attractive machine learning framework for obtaining solutions to partial differential equations(PDEs).PINNs embed initial,boundary,and PDE constraints into the los...Physics-informed neural networks(PINNs)have become an attractive machine learning framework for obtaining solutions to partial differential equations(PDEs).PINNs embed initial,boundary,and PDE constraints into the loss function.The performance of PINNs is generally affected by both training and sampling.Specifically,training methods focus on how to overcome the training difficulties caused by the special PDE residual loss of PINNs,and sampling methods are concerned with the location and distribution of the sampling points upon which evaluations of PDE residual loss are accomplished.However,a common problem among these original PINNs is that they omit special temporal information utilization during the training or sampling stages when dealing with an important PDE category,namely,time-dependent PDEs,where temporal information plays a key role in the algorithms used.There is one method,called Causal PINN,that considers temporal causality at the training level but not special temporal utilization at the sampling level.Incorporating temporal knowledge into sampling remains to be studied.To fill this gap,we propose a novel temporal causality-based adaptive sampling method that dynamically determines the sampling ratio according to both PDE residual and temporal causality.By designing a sampling ratio determined by both residual loss and temporal causality to control the number and location of sampled points in each temporal sub-domain,we provide a practical solution by incorporating temporal information into sampling.Numerical experiments of several nonlinear time-dependent PDEs,including the Cahn–Hilliard,Korteweg–de Vries,Allen–Cahn and wave equations,show that our proposed sampling method can improve the performance.We demonstrate that using such a relatively simple sampling method can improve prediction performance by up to two orders of magnitude compared with the results from other methods,especially when points are limited.展开更多
This article investigates the issue of finite-time state estimation in coupled neural networks under random mixed cyberattacks,in which the Markov process is used to model the mixed cyberattacks.To optimize the utiliz...This article investigates the issue of finite-time state estimation in coupled neural networks under random mixed cyberattacks,in which the Markov process is used to model the mixed cyberattacks.To optimize the utilization of channel resources,a decentralized event-triggered mechanism is adopted during the information transmission.By establishing the augmentation system and constructing the Lyapunov function,sufficient conditions are obtained for the system to be finite-time bounded and satisfy the H_(∞ )performance index.Then,under these conditions,a suitable state estimator gain is obtained.Finally,the feasibility of the method is verified by a given illustrative example.展开更多
In this paper, the global stability of Takagi-Sugeno （TS） uncertain stochastic fuzzy recurrent neural networks with discrete and distributed time-varying delays （TSUSFRNNs） is considered. A novel LMI-based stabili...In this paper, the global stability of Takagi-Sugeno （TS） uncertain stochastic fuzzy recurrent neural networks with discrete and distributed time-varying delays （TSUSFRNNs） is considered. A novel LMI-based stability criterion is obtained by using Lyapunov functional theory to guarantee the asymptotic stability of TSUSFRNNs. The proposed stability conditions are demonstrated through numerical examples. Furthermore, the supplementary requirement that the time derivative of time-varying delays must be smaller than one is removed. Comparison results are demonstrated to show that the proposed method is more able to guarantee the widest stability region than the other methods available in the existing literature.展开更多
In this paper, global robust stability of uncertain stochastic recurrent neural networks with Markovian jumping parameters is considered. A novel Linear matrix inequal- ity（LMI） based stability criterion is obtained...In this paper, global robust stability of uncertain stochastic recurrent neural networks with Markovian jumping parameters is considered. A novel Linear matrix inequal- ity（LMI） based stability criterion is obtained to guarantee the asymptotic stability of uncertain stochastic recurrent neural networks with Markovian jumping parameters. The results are derived by using the Lyapunov functional technique, Lipchitz condition and S-procuture. Finally, numerical examples are given to demonstrate the correctness of the theoretical results. Our results are also compared with results discussed in [31] and [34] to show the effectiveness and conservativeness.展开更多
Deep neural networks(DNN)are widely used in image recognition,image classification,and other fields.However,as the model size increases,the DNN hardware accelerators face the challenge of higher area overhead and ener...Deep neural networks(DNN)are widely used in image recognition,image classification,and other fields.However,as the model size increases,the DNN hardware accelerators face the challenge of higher area overhead and energy consumption.In recent years,stochastic computing(SC)has been considered a way to realize deep neural networks and reduce hardware consumption.A probabilistic compensation algorithm is proposed to solve the accuracy problem of stochastic calculation,and a fully parallel neural network accelerator based on a deterministic method is designed.The software simulation results show that the accuracy of the probability compensation algorithm on the CIFAR-10 data set is 95.32%,which is 14.98%higher than that of the traditional SC algorithm.The accuracy of the deterministic algorithm on the CIFAR-10 dataset is 95.06%,which is 14.72%higher than that of the traditional SC algorithm.The results of Very Large Scale Integration Circuit(VLSI)hardware tests show that the normalized energy efficiency of the fully parallel neural network accelerator based on the deterministic method is improved by 31%compared with the circuit based on binary computing.展开更多
This paper is concerned with the problem of robust stability for a class of Markovian jumping stochastic neural networks （MJSNNs） subject to mode-dependent time-varying interval delay and state-multiplicative noise....This paper is concerned with the problem of robust stability for a class of Markovian jumping stochastic neural networks （MJSNNs） subject to mode-dependent time-varying interval delay and state-multiplicative noise. Based on the Lyapunov-Krasovskii functional and a stochastic analysis approach, some new delay-dependent sufficient conditions are obtained in the linear matrix inequality （LMI） format such that delayed MJSNNs are globally asymptotically stable in the mean-square sense for all admissible uncertainties. An important feature of the results is that the stability criteria are dependent on not only the lower bound and upper bound of delay for all modes but also the covariance matrix consisting of the correlation coefficient. Numerical examples are given to illustrate the effectiveness.展开更多
This paper studies the problem of linear matrix inequality （LMI） approach to robust stability analysis for stochastic neural networks with a time-varying delay. By developing a delay decomposition approach, the info...This paper studies the problem of linear matrix inequality （LMI） approach to robust stability analysis for stochastic neural networks with a time-varying delay. By developing a delay decomposition approach, the information of the delayed plant states can be taken into full consideration. Based on the new Lyapunov-Krasovskii functional, some inequality techniques and stochastic stability theory, new delay-dependent stability criteria are obtained in terms of LMIs. The proposed results prove the less conservatism, which are realized by choosing new Lyapunov matrices in the decomposed integral intervals. Finally, numerical examples are provided to demonstrate the less conservatism and effectiveness of the proposed LMI method.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.1217211 and 12372244).
文摘Physics informed neural networks(PINNs)are a deep learning approach designed to solve partial differential equations(PDEs).Accurately learning the initial conditions is crucial when employing PINNs to solve PDEs.However,simply adjusting weights and imposing hard constraints may not always lead to better learning of the initial conditions;sometimes it even makes it difficult for the neural networks to converge.To enhance the accuracy of PINNs in learning the initial conditions,this paper proposes a novel strategy named causally enhanced initial conditions(CEICs).This strategy works by embedding a new loss in the loss function:the loss is constructed by the derivative of the initial condition and the derivative of the neural network at the initial condition.Furthermore,to respect the causality in learning the derivative,a novel causality coefficient is introduced for the training when selecting multiple derivatives.Additionally,because CEICs can provide more accurate pseudo-labels in the first subdomain,they are compatible with the temporal-marching strategy.Experimental results demonstrate that CEICs outperform hard constraints and improve the overall accuracy of pre-training PINNs.For the 1D-Korteweg–de Vries,reaction and convection equations,the CEIC method proposed in this paper reduces the relative error by at least 60%compared to the previous methods.
基金Project supported by the National Natural Science Foundation of China(Grant No.12305303)the Natural Science Foundation of Hunan Province of China(Grant Nos.2023JJ40520,2024JJ2044,and 2021JJ40444)+3 种基金the Science and Technology Innovation Program of Hunan Province,China(Grant No.2020RC3054)the Postgraduate Scientific Research Innovation Project of Hunan Province,China(Grant No.CX20240831)the Natural Science Basic Research Plan in the Shaanxi Province of China(Grant No.2023-JC-QN0015)the Doctoral Research Fund of University of South China(Grant No.200XQD033)。
文摘The single event effects(SEEs)evaluations caused by atmospheric neutrons were conducted on three different convolutional neural network(CNN)models(Yolov3,MNIST,and ResNet50)in the atmospheric neutron irradiation spectrometer(ANIS)at the China Spallation Neutron Source(CSNS).The Yolov3 and MNIST models were implemented on the XILINX28-nm system-on-chip(So C).Meanwhile,the Yolov3 and ResNet50 models were deployed on the XILINX 16-nm Fin FET Ultra Scale+MPSoC.The atmospheric neutron SEEs on the tested CNN systems were comprehensively evaluated from six aspects,including chip type,network architecture,deployment methods,inference time,datasets,and the position of the anchor boxes.The various types of SEE soft errors,SEE cross-sections,and their distribution were analyzed to explore the radiation sensitivities and rules of 28-nm and 16-nm SoC.The current research can provide the technology support of radiation-resistant design of CNN system for developing and applying high-reliability,long-lifespan domestic artificial intelligence chips.
文摘This paper addresses the issue of nonfragile state estimation for memristive recurrent neural networks with proportional delay and sensor saturations. In practical engineering, numerous unnecessary signals are transmitted to the estimator through the networks, which increases the burden of communication bandwidth. A dynamic event-triggered mechanism,instead of a static event-triggered mechanism, is employed to select useful data. By constructing a meaningful Lyapunov–Krasovskii functional, a delay-dependent criterion is derived in terms of linear matrix inequalities for ensuring the global asymptotic stability of the augmented system. In the end, two numerical simulations are employed to illustrate the feasibility and validity of the proposed theoretical results.
文摘To avoid the aerodynamic performance loss of airfoil at non-design state which often appears in single point design optimization, and to improve the adaptability to the uncertain factors in actual flight environment, a two-dimensional stochastic airfoil optimization design method based on neural networks is presented. To provide highly efficient and credible analysis, four BP neural networks are built as surrogate models to predict the airfoil aerodynamic coefficients and geometry parameter. These networks are combined with the probability density function obeying normal distribution and the genetic algorithm, thus forming an optimization design method. Using the method, for GA（W）-2 airfoil, a stochastic optimization is implemented in a two-dimensional flight area about Mach number and angle of attack. Compared with original airfoil and single point optimization design airfoil, results show that the two-dimensional stochastic method can improve the performance in a specific flight area, and increase the airfoil adaptability to the stochastic changes of multiple flight parameters.
基金The authors acknowledge the funding provided by the National Key R&D Program of China(2021YFA1401200)Beijing Outstanding Young Scientist Program(BJJWZYJH01201910007022)+2 种基金National Natural Science Foundation of China(No.U21A20140,No.92050117,No.62005017)programBeijing Municipal Science&Technology Commission,Administrative Commission of Zhongguancun Science Park(No.Z211100004821009)This work was supported by the Synergetic Extreme Condition User Facility(SECUF).
文摘Optical neural networks have significant advantages in terms of power consumption,parallelism,and high computing speed,which has intrigued extensive attention in both academic and engineering communities.It has been considered as one of the powerful tools in promoting the fields of imaging processing and object recognition.However,the existing optical system architecture cannot be reconstructed to the realization of multi-functional artificial intelligence systems simultaneously.To push the development of this issue,we propose the pluggable diffractive neural networks(P-DNN),a general paradigm resorting to the cascaded metasurfaces,which can be applied to recognize various tasks by switching internal plug-ins.As the proof-of-principle,the recognition functions of six types of handwritten digits and six types of fashions are numerical simulated and experimental demonstrated at near-infrared regimes.Encouragingly,the proposed paradigm not only improves the flexibility of the optical neural networks but paves the new route for achieving high-speed,low-power and versatile artificial intelligence systems.
基金supported by the National Natural Science Foundation of China under Grant No. 60874088 and No. 11072059the Scientific Research Fund of Yunnan Province under Grant No. 2010ZC150the Scientific Research Fund of Yunnan Provincial Education Department under Grant No. 07Y10085
文摘In this article, we consider the global chaotic synchronization of general cou- pled neural networks, in which subsystems have both discrete and distributed delays. Stochastic perturbations between subsystems are also considered. On the basis of two sim- ple adaptive pinning feedback control schemes, Lyapunov functional method, and stochas- tic analysis approach, several sufficient conditions are developed to guarantee global syn- chronization of the coupled neural networks with two kinds of delay couplings, even if only partial states of the nodes are coupled. The outer-coupling matrices may be symmetric or asymmetric. Unlike existing results that an isolate node is introduced as the pinning target, we pin to help the network realizing synchronization without introducing any iso- late node when the network is not synchronized. As a by product, sufficient conditions under which the network realizes synchronization without control are derived. Numerical simulations confirm the effectiveness of the obtained results.
基金supported by DST Project(Grant No.SR/FTP/MS-039/2011)
文摘In this paper, the global asymptotic stability problem of Markovian jumping stochastic Cohen-Grossberg neural networks with discrete and distributed time-varying delays （MJSCGNNs） is considered. A novel LMI-based stability criterion is obtained by constructing a new Lyapunov functional to guarantee the asymptotic stability of MJSCGNNs. Our results can be easily verified and they are also less restrictive than previously known criteria and can be applied to Cohen-Grossberg neural networks, recurrent neural networks, and cellular neural networks. Finally, the proposed stability conditions are demonstrated with numerical examples.
基金support of the National Science Foundation(ECCS-1916839 and DMR-2202268).
文摘In a very recent study,Prof.Lingling Huang and co-workers proposed and demonstrated reconfigurable optical neural networks based on cascaded metasurfaces.By fixing one metasurface and switching the other pluggable metasurfaces,the neural networks,which operate at near-infrared wavelengths,can perform distinct recognition tasks for handwritten digits and fashion products.This innovative device opens up an avenue for all-optical,high-speed,low-power,and multifunctional artificial intelligence systems.
基金the Ministry of Science and Technology of India(Grant No.DST/Inspire Fellowship/2010/[293]/dt.18/03/2011)
文摘We investigate the stochastic asymptotical synchronization of chaotic Markovian jumping fuzzy cellular neural networks （MJFCNNs） with discrete, unbounded distributed delays, and the Wiener process based on sampled-data control using the linear matrix inequality （LMI） approach. The Lyapunov–Krasovskii functional combined with the input delay approach as well as the free-weighting matrix approach is employed to derive several sufficient criteria in terms of LMIs to ensure that the delayed MJFCNNs with the Wiener process is stochastic asymptotical synchronous. Restrictions （e.g., time derivative is smaller than one） are removed to obtain a proposed sampled-data controller. Finally, a numerical example is provided to demonstrate the reliability of the derived results.
基金Project supported by the National Natural Science Foundation of China (Grant Nos. U20A20227,62076208, and 62076207)Chongqing Talent Plan “Contract System” Project (Grant No. CQYC20210302257)+3 种基金National Key Laboratory of Smart Vehicle Safety Technology Open Fund Project (Grant No. IVSTSKL-202309)the Chongqing Technology Innovation and Application Development Special Major Project (Grant No. CSTB2023TIAD-STX0020)College of Artificial Intelligence, Southwest UniversityState Key Laboratory of Intelligent Vehicle Safety Technology
文摘Neuromorphic computing,inspired by the human brain,uses memristor devices for complex tasks.Recent studies show that self-organizing random nanowires can implement neuromorphic information processing,enabling data analysis.This paper presents a model based on these nanowire networks,with an improved conductance variation profile.We suggest using these networks for temporal information processing via a reservoir computing scheme and propose an efficient data encoding method using voltage pulses.The nanowire network layer generates dynamic behaviors for pulse voltages,allowing time series prediction analysis.Our experiment uses a double stochastic nanowire network architecture for processing multiple input signals,outperforming traditional reservoir computing in terms of fewer nodes,enriched dynamics and improved prediction accuracy.Experimental results confirm the high accuracy of this architecture on multiple real-time series datasets,making neuromorphic nanowire networks promising for physical implementation of reservoir computing.
基金National Natural Science Foundation of China(1180500311947102+4 种基金12004005)Natural Science Foundation of Anhui Province(2008085MA162008085QA26)University Synergy Innovation Program of Anhui Province(GXXT-2022-039)State Key Laboratory of Advanced Electromagnetic Technology(Grant No.AET 2024KF006)。
文摘High-resolution flow field data has important applications in meteorology,aerospace engineering,high-energy physics and other fields.Experiments and numerical simulations are two main ways to obtain high-resolution flow field data,while the high experiment cost and computing resources for simulation hinder the specificanalysis of flow field evolution.With the development of deep learning technology,convolutional neural networks areused to achieve high-resolution reconstruction of the flow field.In this paper,an ordinary convolutional neuralnetwork and a multi-time-path convolutional neural network are established for the ablative Rayleigh-Taylorinstability.These two methods can reconstruct the high-resolution flow field in just a few seconds,and further greatlyenrich the application of high-resolution reconstruction technology in fluid instability.Compared with the ordinaryconvolutional neural network,the multi-time-path convolutional neural network model has smaller error and canrestore more details of the flow field.The influence of low-resolution flow field data obtained by the two poolingmethods on the convolutional neural networks model is also discussed.
基金supported by National Natural Science Foundation of China (No.62001135)the Joint funds for Regional Innovation and Development of the National Natural Science Foundation of China(No.U21A20449)the Beijing Natural Science Foundation Haidian Original Innovation Joint Fund (No.L232002)
文摘UAV-aided cellular networks,millimeter wave(mm-wave) communications and multi-antenna techniques are viewed as promising components of the solution for beyond-5G(B5G) and even 6G communications.By leveraging the power of stochastic geometry,this paper aims at providing an effective framework for modeling and analyzing a UAV-aided heterogeneous cellular network,where the terrestrial base stations(TBSs) and the UAV base stations(UBSs) coexist,and the UBSs are provided with mm-wave and multi-antenna techniques.By modeling the TBSs as a PPP and the UBSs as a Matern hard-core point process of type Ⅱ(MPH-Ⅱ),approximated but accurate analytical results for the average rate of the typical user of both tiers are derived through an approximation method based on the mean interference-to-signal ratio(MISR) gain.The influence of some relevant parameters is discussed in detail,and some insights into the network deployment and optimization are revealed.Numerical results show that some trade-offs are worthy of being considered,such as the antenna array size,the altitude of the UAVs and the power control factor of the UBSs.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.42005003 and 41475094).
文摘Efficiently solving partial differential equations(PDEs)is a long-standing challenge in mathematics and physics research.In recent years,the rapid development of artificial intelligence technology has brought deep learning-based methods to the forefront of research on numerical methods for partial differential equations.Among them,physics-informed neural networks(PINNs)are a new class of deep learning methods that show great potential in solving PDEs and predicting complex physical phenomena.In the field of nonlinear science,solitary waves and rogue waves have been important research topics.In this paper,we propose an improved PINN that enhances the physical constraints of the neural network model by adding gradient information constraints.In addition,we employ meta-learning optimization to speed up the training process.We apply the improved PINNs to the numerical simulation and prediction of solitary and rogue waves.We evaluate the accuracy of the prediction results by error analysis.The experimental results show that the improved PINNs can make more accurate predictions in less time than that of the original PINNs.
基金Project supported by the Key National Natural Science Foundation of China(Grant No.62136005)the National Natural Science Foundation of China(Grant Nos.61922087,61906201,and 62006238)。
文摘Physics-informed neural networks(PINNs)have become an attractive machine learning framework for obtaining solutions to partial differential equations(PDEs).PINNs embed initial,boundary,and PDE constraints into the loss function.The performance of PINNs is generally affected by both training and sampling.Specifically,training methods focus on how to overcome the training difficulties caused by the special PDE residual loss of PINNs,and sampling methods are concerned with the location and distribution of the sampling points upon which evaluations of PDE residual loss are accomplished.However,a common problem among these original PINNs is that they omit special temporal information utilization during the training or sampling stages when dealing with an important PDE category,namely,time-dependent PDEs,where temporal information plays a key role in the algorithms used.There is one method,called Causal PINN,that considers temporal causality at the training level but not special temporal utilization at the sampling level.Incorporating temporal knowledge into sampling remains to be studied.To fill this gap,we propose a novel temporal causality-based adaptive sampling method that dynamically determines the sampling ratio according to both PDE residual and temporal causality.By designing a sampling ratio determined by both residual loss and temporal causality to control the number and location of sampled points in each temporal sub-domain,we provide a practical solution by incorporating temporal information into sampling.Numerical experiments of several nonlinear time-dependent PDEs,including the Cahn–Hilliard,Korteweg–de Vries,Allen–Cahn and wave equations,show that our proposed sampling method can improve the performance.We demonstrate that using such a relatively simple sampling method can improve prediction performance by up to two orders of magnitude compared with the results from other methods,especially when points are limited.
基金Project supported by the National Natural Science Foundation of China(Grant No.62303016)the Research and Development Project of Engineering Research Center of Biofilm Water Purification and Utilization Technology of the Ministry of Education of China(Grant No.BWPU2023ZY02)+1 种基金the University Synergy Innovation Program of Anhui Province,China(Grant No.GXXT-2023-020)the Key Project of Natural Science Research in Universities of Anhui Province,China(Grant No.2024AH050171).
文摘This article investigates the issue of finite-time state estimation in coupled neural networks under random mixed cyberattacks,in which the Markov process is used to model the mixed cyberattacks.To optimize the utilization of channel resources,a decentralized event-triggered mechanism is adopted during the information transmission.By establishing the augmentation system and constructing the Lyapunov function,sufficient conditions are obtained for the system to be finite-time bounded and satisfy the H_(∞ )performance index.Then,under these conditions,a suitable state estimator gain is obtained.Finally,the feasibility of the method is verified by a given illustrative example.
文摘In this paper, the global stability of Takagi-Sugeno （TS） uncertain stochastic fuzzy recurrent neural networks with discrete and distributed time-varying delays （TSUSFRNNs） is considered. A novel LMI-based stability criterion is obtained by using Lyapunov functional theory to guarantee the asymptotic stability of TSUSFRNNs. The proposed stability conditions are demonstrated through numerical examples. Furthermore, the supplementary requirement that the time derivative of time-varying delays must be smaller than one is removed. Comparison results are demonstrated to show that the proposed method is more able to guarantee the widest stability region than the other methods available in the existing literature.
基金supported by NBHM project grant No.2/48(10)/2011-RD-II/865
文摘In this paper, global robust stability of uncertain stochastic recurrent neural networks with Markovian jumping parameters is considered. A novel Linear matrix inequal- ity（LMI） based stability criterion is obtained to guarantee the asymptotic stability of uncertain stochastic recurrent neural networks with Markovian jumping parameters. The results are derived by using the Lyapunov functional technique, Lipchitz condition and S-procuture. Finally, numerical examples are given to demonstrate the correctness of the theoretical results. Our results are also compared with results discussed in [31] and [34] to show the effectiveness and conservativeness.
文摘Deep neural networks(DNN)are widely used in image recognition,image classification,and other fields.However,as the model size increases,the DNN hardware accelerators face the challenge of higher area overhead and energy consumption.In recent years,stochastic computing(SC)has been considered a way to realize deep neural networks and reduce hardware consumption.A probabilistic compensation algorithm is proposed to solve the accuracy problem of stochastic calculation,and a fully parallel neural network accelerator based on a deterministic method is designed.The software simulation results show that the accuracy of the probability compensation algorithm on the CIFAR-10 data set is 95.32%,which is 14.98%higher than that of the traditional SC algorithm.The accuracy of the deterministic algorithm on the CIFAR-10 dataset is 95.06%,which is 14.72%higher than that of the traditional SC algorithm.The results of Very Large Scale Integration Circuit(VLSI)hardware tests show that the normalized energy efficiency of the fully parallel neural network accelerator based on the deterministic method is improved by 31%compared with the circuit based on binary computing.
基金supported by the National Natural Science Foundation of China (Grant Nos 60534010,60774048,60728307,60804006,60521003)the National High Technology Research and Development Program of China (863 Program) (Grant No 2006AA04Z183)+2 种基金the Natural Science Foundation of Liaoning Province of China (Grant No 20062018)973 Project (Grant No 2009CB320601)111 Project (Grant No B08015)
文摘This paper is concerned with the problem of robust stability for a class of Markovian jumping stochastic neural networks （MJSNNs） subject to mode-dependent time-varying interval delay and state-multiplicative noise. Based on the Lyapunov-Krasovskii functional and a stochastic analysis approach, some new delay-dependent sufficient conditions are obtained in the linear matrix inequality （LMI） format such that delayed MJSNNs are globally asymptotically stable in the mean-square sense for all admissible uncertainties. An important feature of the results is that the stability criteria are dependent on not only the lower bound and upper bound of delay for all modes but also the covariance matrix consisting of the correlation coefficient. Numerical examples are given to illustrate the effectiveness.
基金supported by the Science Foundation of the Department of Science and Technology,New Delhi,India (Grant No.SR/S4/MS:485/07)
文摘This paper studies the problem of linear matrix inequality （LMI） approach to robust stability analysis for stochastic neural networks with a time-varying delay. By developing a delay decomposition approach, the information of the delayed plant states can be taken into full consideration. Based on the new Lyapunov-Krasovskii functional, some inequality techniques and stochastic stability theory, new delay-dependent stability criteria are obtained in terms of LMIs. The proposed results prove the less conservatism, which are realized by choosing new Lyapunov matrices in the decomposed integral intervals. Finally, numerical examples are provided to demonstrate the less conservatism and effectiveness of the proposed LMI method.
