This paper proposes a concurrent neural network model to mitigate non-linear distortion in power amplifiers using a basis function generation approach.The model is designed using polynomial expansion and comprises a f...This paper proposes a concurrent neural network model to mitigate non-linear distortion in power amplifiers using a basis function generation approach.The model is designed using polynomial expansion and comprises a feedforward neural network(FNN)and a convolutional neural network(CNN).The proposed model takes the basic elements that form the bases as input,defined by the generalized memory polynomial(GMP)and dynamic deviation reduction(DDR)models.The FNN generates the basis function and its output represents the basis values,while the CNN generates weights for the corresponding bases.Through the concurrent training of FNN and CNN,the hidden layer coefficients are updated,and the complex multiplication of their outputs yields the trained in-phase/quadrature(I/Q)signals.The proposed model was trained and tested using 300 MHz and 400 MHz broadband data in an orthogonal frequency division multiplexing(OFDM)communication system.The results show that the model achieves an adjacent channel power ratio(ACPR)of less than-48 d B within a 100 MHz integral bandwidth for both the training and test datasets.展开更多
The on-line estimation of the state of charge （SOC） of the batteries is important for the reliable running of the pure electric vehicle in practice. Because a nonlinear feature exists in the batteries and the radial...The on-line estimation of the state of charge （SOC） of the batteries is important for the reliable running of the pure electric vehicle in practice. Because a nonlinear feature exists in the batteries and the radial-basis-function neural network （RBF NN） has good characteristics to solve the nonlinear problem, a practical method for the SOC estimation of batteries based on the RBF NN with a small number of input variables and a simplified structure is proposed. Firstly, in this paper, the model of on-line SOC estimation with the RBF NN is set. Secondly, four important factors for estimating the SOC are confirmed based on the contribution analysis method, which simplifies the input variables of the RBF NN and enhttnces the real-time performance of estimation. FiItally, the pure electric buses with LiFePO4 Li-ion batteries running during the period of the 2010 Shanghai World Expo are considered as the experimental object. The performance of the SOC estimation is validated and evaluated by the battery data from the electric vehicle.展开更多
This paper investigates interception missiles’trajectory tracking guidance problem under wind field and external disturbances in the boost phase.Indeed,the velocity control in such trajectory tracking guidance system...This paper investigates interception missiles’trajectory tracking guidance problem under wind field and external disturbances in the boost phase.Indeed,the velocity control in such trajectory tracking guidance systems of missiles is challenging.As our contribution,the velocity control channel is designed to deal with the intractable velocity problem and improve tracking accuracy.The global prescribed performance function,which guarantees the tracking error within the set range and the global convergence of the tracking guidance system,is first proposed based on the traditional PPF.Then,a tracking guidance strategy is derived using the integral sliding mode control techniques to make the sliding manifold and tracking errors converge to zero and avoid singularities.Meanwhile,an improved switching control law is introduced into the designed tracking guidance algorithm to deal with the chattering problem.A back propagation neural network(BPNN)extended state observer(BPNNESO)is employed in the inner loop to identify disturbances.The obtained results indicate that the proposed tracking guidance approach achieves the trajectory tracking guidance objective without and with disturbances and outperforms the existing tracking guidance schemes with the lowest tracking errors,convergence times,and overshoots.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
The alternate combinational approach of genetic algorithm and neural network （AGANN） has been presented to correct the systematic error of the density functional theory （DFT） calculation. It treats the DFT as a bl...The alternate combinational approach of genetic algorithm and neural network （AGANN） has been presented to correct the systematic error of the density functional theory （DFT） calculation. It treats the DFT as a black box and models the error through external statistical information. As a demonstration, the ACANN method has been applied in the correction of the lattice energies from the DFT calculation for 72 metal halides and hydrides. Through the AGANN correction, the mean absolute value of the relative errors of the calculated lattice energies to the experimental values decreases from 4.93% to 1.20% in the testing set. For comparison, the neural network approach reduces the mean value to 2.56%. And for the common combinational approach of genetic algorithm and neural network, the value drops to 2.15%. The multiple linear regression method almost has no correction effect here.展开更多
The air cooler is an important equipment in the petroleum refining industry.Ammonium chloride(NH4 Cl)deposition-induced corrosion is one of its main failure forms.In this study,the ammonium salt crystallization temper...The air cooler is an important equipment in the petroleum refining industry.Ammonium chloride(NH4 Cl)deposition-induced corrosion is one of its main failure forms.In this study,the ammonium salt crystallization temperature is chosen as the key decision variable of NH4 Cl deposition-induced corrosion through in-depth mechanism research and experimental analysis.The functional link neural network(FLNN)is adopted as the basic algorithm for modeling because of its advantages in dealing with non-linear problems and its fast-computational ability.A hybrid FLNN attached to a small norm is built to improve the generalization performance of the model.Then,the trained model is used to predict the NH4 Cl salt crystallization temperature in the air cooler of a sour water stripper plant.Experimental results show the proposed improved FLNN algorithm can achieve better generalization performance than the PLS,the back propagation neural network,and the conventional FLNN models.展开更多
The design of an efficient one-way hash function with good performance is a hot spot in modern cryptography researches. In this paper, a hash function construction method based on cell neural network with hyper-chaos ...The design of an efficient one-way hash function with good performance is a hot spot in modern cryptography researches. In this paper, a hash function construction method based on cell neural network with hyper-chaos characteristics is proposed. First, the chaos sequence is gotten by iterating cellular neural network with Runge Kutta algorithm, and then the chaos sequence is iterated with the message. The hash code is obtained through the corre- sponding transform of the latter chaos sequence. Simulation and analysis demonstrate that the new method has the merit of convenience, high sensitivity to initial values, good hash performance, especially the strong stability.展开更多
In this paper, coexistence and local Mittag–Leffler stability of fractional-order recurrent neural networks with discontinuous activation functions are addressed. Because of the discontinuity of the activation functi...In this paper, coexistence and local Mittag–Leffler stability of fractional-order recurrent neural networks with discontinuous activation functions are addressed. Because of the discontinuity of the activation function, Filippov solution of the neural network is defined. Based on Brouwer's fixed point theorem and definition of Mittag–Leffler stability, sufficient criteria are established to ensure the existence of (2k + 3)~n (k ≥ 1) equilibrium points, among which (k + 2)~n equilibrium points are locally Mittag–Leffler stable. Compared with the existing results, the derived results cover local Mittag–Leffler stability of both fractional-order and integral-order recurrent neural networks. Meanwhile discontinuous networks might have higher storage capacity than the continuous ones. Two numerical examples are elaborated to substantiate the effective of the theoretical results.展开更多
In this paper, new delay-dependent stability criteria for asymptotic stability of neural networks with time-varying delays are derived. The stability conditions are represented in terms of linear matrix inequalities ...In this paper, new delay-dependent stability criteria for asymptotic stability of neural networks with time-varying delays are derived. The stability conditions are represented in terms of linear matrix inequalities （LMIs） by constructing new Lyapunov-Krasovskii functional. The proposed functional has an augmented quadratic form with states as well as the nonlinear function to consider the sector and the slope constraints. The less conservativeness of the proposed stability criteria can be guaranteed by using convex properties of the nonlinear function which satisfies the sector and slope bound. Numerical examples are presented to show the effectiveness of the proposed method.展开更多
A new type of neural network is described, which is basing on Fourier series, and the activation transfer function in its neuron model is sinusoid, ft can approximate to any function, which is continuum in every segme...A new type of neural network is described, which is basing on Fourier series, and the activation transfer function in its neuron model is sinusoid, ft can approximate to any function, which is continuum in every segment, with any precision with by layers only. We also provide the computer approach emulation results of different kinds of static function.展开更多
In this paper, the multistability issue is discussed for delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions. Based on a fixed theorem and stability definition,...In this paper, the multistability issue is discussed for delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions. Based on a fixed theorem and stability definition, sufficient criteria are established for the existence and stability of multiple equilibria of complex-valued recurrent neural networks. The number of stable equilibria is larger than that of real-valued recurrent neural networks, which can be used to achieve high-capacity associative memories. One numerical example is provided to show the effectiveness and superiority of the presented results.展开更多
The finite-time Mittag-Leffler synchronization is investigated for fractional-order delayed memristive neural networks(FDMNN)with parameters uncertainty and discontinuous activation functions.The relevant results are ...The finite-time Mittag-Leffler synchronization is investigated for fractional-order delayed memristive neural networks(FDMNN)with parameters uncertainty and discontinuous activation functions.The relevant results are obtained under the framework of Filippov for such systems.Firstly,the novel feedback controller,which includes the discontinuous functions and time delays,is proposed to investigate such systems.Secondly,the conditions on finite-time Mittag-Leffler synchronization of FDMNN are established according to the properties of fractional-order calculus and inequality analysis technique.At the same time,the upper bound of the settling time for Mittag-Leffler synchronization is accurately estimated.In addition,by selecting the appropriate parameters of the designed controller and utilizing the comparison theorem for fractional-order systems,the global asymptotic synchronization is achieved as a corollary.Finally,a numerical example is given to indicate the correctness of the obtained conclusions.展开更多
Characteristics of the Internet traffic data flow are studied based on the chaos theory. A phase space that is isometric with the network dynamic system is reconstructed by using the single variable time series of a n...Characteristics of the Internet traffic data flow are studied based on the chaos theory. A phase space that is isometric with the network dynamic system is reconstructed by using the single variable time series of a network flow. Some parameters, such as the correlative dimension and the Lyapunov exponent are calculated, and the chaos characteristic is proved to exist in Internet traffic data flows. A neural network model is construct- ed based on radial basis function （RBF） to forecast actual Internet traffic data flow. Simulation results show that, compared with other forecasts of the forward-feedback neural network, the forecast of the RBF neural network based on the chaos theory has faster learning capacity and higher forecasting accuracy.展开更多
Recently, wavelet neural networks have become a popular tool for non-linear functional approximation. Wavelet neural networks, which basis functions are orthonormal scalling functions, are more suitable in approximati...Recently, wavelet neural networks have become a popular tool for non-linear functional approximation. Wavelet neural networks, which basis functions are orthonormal scalling functions, are more suitable in approximating to function. Based on it, approximating to NLAR(p) with wavelet neural networks is studied.展开更多
This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that th...This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that the outputs of the output layer in the FNNs for classification correspond to the estimates of posteriori probability of the input pattern samples with desired outputs 1 or 0. The theorem for the generalized kernel function in the radial basis function networks (RBFN) is given. For an 2-layer perceptron network (2-LPN). an idea of using extended samples to improve generalization capability is proposed. Finally. the experimental results of radar target classification are given to verify the generaliztion capability of the RBFNs.展开更多
Artificial neural networks(ANNs)are a core component of artificial intelligence and are frequently used in machine learning.In this report,we investigate the use of ANNs to recover the saturated signals acquired in hi...Artificial neural networks(ANNs)are a core component of artificial intelligence and are frequently used in machine learning.In this report,we investigate the use of ANNs to recover the saturated signals acquired in highenergy particle and nuclear physics experiments.The inherent properties of the detector and hardware imply that particles with relatively high energies probably often generate saturated signals.Usually,these saturated signals are discarded during data processing,and therefore,some useful information is lost.Thus,it is worth restoring the saturated signals to their normal form.The mapping from a saturated signal waveform to a normal signal waveform constitutes a regression problem.Given that the scintillator and collection usually do not form a linear system,typical regression methods such as multi-parameter fitting are not immediately applicable.One important advantage of ANNs is their capability to process nonlinear regression problems.To recover the saturated signal,three typical ANNs were tested including backpropagation(BP),simple recurrent(Elman),and generalized radial basis function(GRBF)neural networks(NNs).They represent a basic network structure,a network structure with feedback,and a network structure with a kernel function,respectively.The saturated waveforms were produced mainly by the environmental gamma in a liquid scintillation detector for the China Dark Matter Detection Experiment(CDEX).The training and test data sets consisted of 6000 and 3000 recordings of background radiation,respectively,in which saturation was simulated by truncating each waveform at 40%of the maximum signal.The results show that the GBRF-NN performed best as measured using a Chi-squared test to compare the original and reconstructed signals in the region in which saturation was simulated.A comparison of the original and reconstructed signals in this region shows that the GBRF neural network produced the best performance.This ANN demonstrates a powerful efficacy in terms of solving the saturation recovery problem.The proposed method outlines new ideas and possibilities for the recovery of saturated signals in high-energy particle and nuclear physics experiments.This study also illustrates an innovative application of machine learning in the analysis of experimental data in particle physics.展开更多
Parallel multi-thread processing in advanced intelligent processors is the core to realize high-speed and high-capacity signal processing systems.Optical neural network(ONN)has the native advantages of high paralleliz...Parallel multi-thread processing in advanced intelligent processors is the core to realize high-speed and high-capacity signal processing systems.Optical neural network(ONN)has the native advantages of high parallelization,large bandwidth,and low power consumption to meet the demand of big data.Here,we demonstrate the dual-layer ONN with Mach-Zehnder interferometer(MZI)network and nonlinear layer,while the nonlinear activation function is achieved by optical-electronic signal conversion.Two frequency components from the microcomb source carrying digit datasets are simultaneously imposed and intelligently recognized through the ONN.We successfully achieve the digit classification of different frequency components by demultiplexing the output signal and testing power distribution.Efficient parallelization feasibility with wavelength division multiplexing is demonstrated in our high-dimensional ONN.This work provides a high-performance architecture for future parallel high-capacity optical analog computing.展开更多
In this paper, we investigate the dynamics and the global exponential stability of a new class of Hopfield neural network with time-varying and distributed delays. In fact, the properties of norms and the contraction ...In this paper, we investigate the dynamics and the global exponential stability of a new class of Hopfield neural network with time-varying and distributed delays. In fact, the properties of norms and the contraction principle are adjusted to ensure the existence as well as the uniqueness of the pseudo almost periodic solution, which is also its derivative pseudo almost periodic. This results are without resorting to the theory of exponential dichotomy. Furthermore, by employing the suitable Lyapunov function, some delayindependent sufficient conditions are derived for exponential convergence. The main originality lies in the fact that spaces considered in this paper generalize the notion of periodicity and almost periodicity. Lastly, two examples are given to demonstrate the validity of the proposed theoretical results.展开更多
This paper concernes analysis for the global exponential stability of a class of recurrent neural networks with mixed discrete and distributed delays. It first proves the existence and uniqueness of the balance point,...This paper concernes analysis for the global exponential stability of a class of recurrent neural networks with mixed discrete and distributed delays. It first proves the existence and uniqueness of the balance point, then by employing the Lyapunov-Krasovskii functional and Young inequality, it gives the sufficient condition of global exponential stability of cellular neural network with mixed discrete and distributed delays, in addition, the example is provided to illustrate the applicability of the result.展开更多
This paper presents a method used to the numeral eddy current sensor modelling based on the genetic neural network to settle its nonlinear problem. The principle and algorithms of genetic neural network are introduced...This paper presents a method used to the numeral eddy current sensor modelling based on the genetic neural network to settle its nonlinear problem. The principle and algorithms of genetic neural network are introduced. In this method, the nonlinear model parameters of the numeral eddy current sensor are optimized by genetic neural network （GNN） according to measurement data. So the method remains both the global searching ability of genetic algorithm and the good local searching ability of neural network. The nonlinear model has the advantages of strong robustness, on-line modelling and high precision. The maximum nonlinearity error can be reduced to 0.037% by using GNN. However, the maximum nonlinearity error is 0.075% using the least square method.展开更多
基金supported by ZTE Industry-University-Institute Cooperation Funds under Grant No.HC-CN-20220722010。
文摘This paper proposes a concurrent neural network model to mitigate non-linear distortion in power amplifiers using a basis function generation approach.The model is designed using polynomial expansion and comprises a feedforward neural network(FNN)and a convolutional neural network(CNN).The proposed model takes the basic elements that form the bases as input,defined by the generalized memory polynomial(GMP)and dynamic deviation reduction(DDR)models.The FNN generates the basis function and its output represents the basis values,while the CNN generates weights for the corresponding bases.Through the concurrent training of FNN and CNN,the hidden layer coefficients are updated,and the complex multiplication of their outputs yields the trained in-phase/quadrature(I/Q)signals.The proposed model was trained and tested using 300 MHz and 400 MHz broadband data in an orthogonal frequency division multiplexing(OFDM)communication system.The results show that the model achieves an adjacent channel power ratio(ACPR)of less than-48 d B within a 100 MHz integral bandwidth for both the training and test datasets.
基金Project supported by the National High Technology Research and Development Program of China (Grant No. 2011AA110303)the Beijing Municipal Science & Technology Project,China (Grant No. Z111100064311001)
文摘The on-line estimation of the state of charge （SOC） of the batteries is important for the reliable running of the pure electric vehicle in practice. Because a nonlinear feature exists in the batteries and the radial-basis-function neural network （RBF NN） has good characteristics to solve the nonlinear problem, a practical method for the SOC estimation of batteries based on the RBF NN with a small number of input variables and a simplified structure is proposed. Firstly, in this paper, the model of on-line SOC estimation with the RBF NN is set. Secondly, four important factors for estimating the SOC are confirmed based on the contribution analysis method, which simplifies the input variables of the RBF NN and enhttnces the real-time performance of estimation. FiItally, the pure electric buses with LiFePO4 Li-ion batteries running during the period of the 2010 Shanghai World Expo are considered as the experimental object. The performance of the SOC estimation is validated and evaluated by the battery data from the electric vehicle.
基金the National Natural Science Foundation of China(Grant No.12072090).
文摘This paper investigates interception missiles’trajectory tracking guidance problem under wind field and external disturbances in the boost phase.Indeed,the velocity control in such trajectory tracking guidance systems of missiles is challenging.As our contribution,the velocity control channel is designed to deal with the intractable velocity problem and improve tracking accuracy.The global prescribed performance function,which guarantees the tracking error within the set range and the global convergence of the tracking guidance system,is first proposed based on the traditional PPF.Then,a tracking guidance strategy is derived using the integral sliding mode control techniques to make the sliding manifold and tracking errors converge to zero and avoid singularities.Meanwhile,an improved switching control law is introduced into the designed tracking guidance algorithm to deal with the chattering problem.A back propagation neural network(BPNN)extended state observer(BPNNESO)is employed in the inner loop to identify disturbances.The obtained results indicate that the proposed tracking guidance approach achieves the trajectory tracking guidance objective without and with disturbances and outperforms the existing tracking guidance schemes with the lowest tracking errors,convergence times,and overshoots.
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supported by the National Basic Research Program of China (973 Program) (Grant No. G2009CB929300)the National Natural Science Foundation of China (Grant No. 60521001 and 60925016)
文摘The alternate combinational approach of genetic algorithm and neural network （AGANN） has been presented to correct the systematic error of the density functional theory （DFT） calculation. It treats the DFT as a black box and models the error through external statistical information. As a demonstration, the ACANN method has been applied in the correction of the lattice energies from the DFT calculation for 72 metal halides and hydrides. Through the AGANN correction, the mean absolute value of the relative errors of the calculated lattice energies to the experimental values decreases from 4.93% to 1.20% in the testing set. For comparison, the neural network approach reduces the mean value to 2.56%. And for the common combinational approach of genetic algorithm and neural network, the value drops to 2.15%. The multiple linear regression method almost has no correction effect here.
基金supported by the National Natural Science Foundation of China(Grant No.51876194,U1909216)the China Petrochemical Corporation Research Project(318023-2)the Zhejiang Public Welfare Technology Research Project(LGG20F030007)。
文摘The air cooler is an important equipment in the petroleum refining industry.Ammonium chloride(NH4 Cl)deposition-induced corrosion is one of its main failure forms.In this study,the ammonium salt crystallization temperature is chosen as the key decision variable of NH4 Cl deposition-induced corrosion through in-depth mechanism research and experimental analysis.The functional link neural network(FLNN)is adopted as the basic algorithm for modeling because of its advantages in dealing with non-linear problems and its fast-computational ability.A hybrid FLNN attached to a small norm is built to improve the generalization performance of the model.Then,the trained model is used to predict the NH4 Cl salt crystallization temperature in the air cooler of a sour water stripper plant.Experimental results show the proposed improved FLNN algorithm can achieve better generalization performance than the PLS,the back propagation neural network,and the conventional FLNN models.
基金supported by Key Program of Natural Science Fund of Tianjin of China (Grant No 07JCZDJC06600)
文摘The design of an efficient one-way hash function with good performance is a hot spot in modern cryptography researches. In this paper, a hash function construction method based on cell neural network with hyper-chaos characteristics is proposed. First, the chaos sequence is gotten by iterating cellular neural network with Runge Kutta algorithm, and then the chaos sequence is iterated with the message. The hash code is obtained through the corre- sponding transform of the latter chaos sequence. Simulation and analysis demonstrate that the new method has the merit of convenience, high sensitivity to initial values, good hash performance, especially the strong stability.
基金Project supported by the Natural Science Foundation of Zhejiang Province,China(Grant Nos.LY18F030023,LY17F030016,and LY18F020028)the National Natural Science Foundation of China(Grant Nos.61503338,61502422,and 61773348)
文摘In this paper, coexistence and local Mittag–Leffler stability of fractional-order recurrent neural networks with discontinuous activation functions are addressed. Because of the discontinuity of the activation function, Filippov solution of the neural network is defined. Based on Brouwer's fixed point theorem and definition of Mittag–Leffler stability, sufficient criteria are established to ensure the existence of (2k + 3)~n (k ≥ 1) equilibrium points, among which (k + 2)~n equilibrium points are locally Mittag–Leffler stable. Compared with the existing results, the derived results cover local Mittag–Leffler stability of both fractional-order and integral-order recurrent neural networks. Meanwhile discontinuous networks might have higher storage capacity than the continuous ones. Two numerical examples are elaborated to substantiate the effective of the theoretical results.
基金Project supported by the Daegu University Research Grant,2009
文摘In this paper, new delay-dependent stability criteria for asymptotic stability of neural networks with time-varying delays are derived. The stability conditions are represented in terms of linear matrix inequalities （LMIs） by constructing new Lyapunov-Krasovskii functional. The proposed functional has an augmented quadratic form with states as well as the nonlinear function to consider the sector and the slope constraints. The less conservativeness of the proposed stability criteria can be guaranteed by using convex properties of the nonlinear function which satisfies the sector and slope bound. Numerical examples are presented to show the effectiveness of the proposed method.
文摘A new type of neural network is described, which is basing on Fourier series, and the activation transfer function in its neuron model is sinusoid, ft can approximate to any function, which is continuum in every segment, with any precision with by layers only. We also provide the computer approach emulation results of different kinds of static function.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.61374094 and 61503338)the Natural Science Foundation of Zhejiang Province,China(Grant No.LQ15F030005)
文摘In this paper, the multistability issue is discussed for delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions. Based on a fixed theorem and stability definition, sufficient criteria are established for the existence and stability of multiple equilibria of complex-valued recurrent neural networks. The number of stable equilibria is larger than that of real-valued recurrent neural networks, which can be used to achieve high-capacity associative memories. One numerical example is provided to show the effectiveness and superiority of the presented results.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.61703312 and 61703313)。
文摘The finite-time Mittag-Leffler synchronization is investigated for fractional-order delayed memristive neural networks(FDMNN)with parameters uncertainty and discontinuous activation functions.The relevant results are obtained under the framework of Filippov for such systems.Firstly,the novel feedback controller,which includes the discontinuous functions and time delays,is proposed to investigate such systems.Secondly,the conditions on finite-time Mittag-Leffler synchronization of FDMNN are established according to the properties of fractional-order calculus and inequality analysis technique.At the same time,the upper bound of the settling time for Mittag-Leffler synchronization is accurately estimated.In addition,by selecting the appropriate parameters of the designed controller and utilizing the comparison theorem for fractional-order systems,the global asymptotic synchronization is achieved as a corollary.Finally,a numerical example is given to indicate the correctness of the obtained conclusions.
文摘Characteristics of the Internet traffic data flow are studied based on the chaos theory. A phase space that is isometric with the network dynamic system is reconstructed by using the single variable time series of a network flow. Some parameters, such as the correlative dimension and the Lyapunov exponent are calculated, and the chaos characteristic is proved to exist in Internet traffic data flows. A neural network model is construct- ed based on radial basis function （RBF） to forecast actual Internet traffic data flow. Simulation results show that, compared with other forecasts of the forward-feedback neural network, the forecast of the RBF neural network based on the chaos theory has faster learning capacity and higher forecasting accuracy.
文摘Recently, wavelet neural networks have become a popular tool for non-linear functional approximation. Wavelet neural networks, which basis functions are orthonormal scalling functions, are more suitable in approximating to function. Based on it, approximating to NLAR(p) with wavelet neural networks is studied.
文摘This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that the outputs of the output layer in the FNNs for classification correspond to the estimates of posteriori probability of the input pattern samples with desired outputs 1 or 0. The theorem for the generalized kernel function in the radial basis function networks (RBFN) is given. For an 2-layer perceptron network (2-LPN). an idea of using extended samples to improve generalization capability is proposed. Finally. the experimental results of radar target classification are given to verify the generaliztion capability of the RBFNs.
基金supported by the ‘‘Detection of very low-flux background neutrons in China Jinping Underground Laboratory’’ project of the National Natural Science Foundation of China(No.11275134)
文摘Artificial neural networks(ANNs)are a core component of artificial intelligence and are frequently used in machine learning.In this report,we investigate the use of ANNs to recover the saturated signals acquired in highenergy particle and nuclear physics experiments.The inherent properties of the detector and hardware imply that particles with relatively high energies probably often generate saturated signals.Usually,these saturated signals are discarded during data processing,and therefore,some useful information is lost.Thus,it is worth restoring the saturated signals to their normal form.The mapping from a saturated signal waveform to a normal signal waveform constitutes a regression problem.Given that the scintillator and collection usually do not form a linear system,typical regression methods such as multi-parameter fitting are not immediately applicable.One important advantage of ANNs is their capability to process nonlinear regression problems.To recover the saturated signal,three typical ANNs were tested including backpropagation(BP),simple recurrent(Elman),and generalized radial basis function(GRBF)neural networks(NNs).They represent a basic network structure,a network structure with feedback,and a network structure with a kernel function,respectively.The saturated waveforms were produced mainly by the environmental gamma in a liquid scintillation detector for the China Dark Matter Detection Experiment(CDEX).The training and test data sets consisted of 6000 and 3000 recordings of background radiation,respectively,in which saturation was simulated by truncating each waveform at 40%of the maximum signal.The results show that the GBRF-NN performed best as measured using a Chi-squared test to compare the original and reconstructed signals in the region in which saturation was simulated.A comparison of the original and reconstructed signals in this region shows that the GBRF neural network produced the best performance.This ANN demonstrates a powerful efficacy in terms of solving the saturation recovery problem.The proposed method outlines new ideas and possibilities for the recovery of saturated signals in high-energy particle and nuclear physics experiments.This study also illustrates an innovative application of machine learning in the analysis of experimental data in particle physics.
基金Peng Xie acknowledges the support from the China Scholarship Council(Grant no.201804910829).
文摘Parallel multi-thread processing in advanced intelligent processors is the core to realize high-speed and high-capacity signal processing systems.Optical neural network(ONN)has the native advantages of high parallelization,large bandwidth,and low power consumption to meet the demand of big data.Here,we demonstrate the dual-layer ONN with Mach-Zehnder interferometer(MZI)network and nonlinear layer,while the nonlinear activation function is achieved by optical-electronic signal conversion.Two frequency components from the microcomb source carrying digit datasets are simultaneously imposed and intelligently recognized through the ONN.We successfully achieve the digit classification of different frequency components by demultiplexing the output signal and testing power distribution.Efficient parallelization feasibility with wavelength division multiplexing is demonstrated in our high-dimensional ONN.This work provides a high-performance architecture for future parallel high-capacity optical analog computing.
文摘In this paper, we investigate the dynamics and the global exponential stability of a new class of Hopfield neural network with time-varying and distributed delays. In fact, the properties of norms and the contraction principle are adjusted to ensure the existence as well as the uniqueness of the pseudo almost periodic solution, which is also its derivative pseudo almost periodic. This results are without resorting to the theory of exponential dichotomy. Furthermore, by employing the suitable Lyapunov function, some delayindependent sufficient conditions are derived for exponential convergence. The main originality lies in the fact that spaces considered in this paper generalize the notion of periodicity and almost periodicity. Lastly, two examples are given to demonstrate the validity of the proposed theoretical results.
基金Project supported by the National Natural Science Foundations of China(Grant No.70871056)the Society Science Foundation from Ministry of Education of China(Grant No.08JA790057)the Advanced Talents'Foundation and Student's Foundation of Jiangsu University,China(Grant Nos.07JDG054 and 07A075)
文摘This paper concernes analysis for the global exponential stability of a class of recurrent neural networks with mixed discrete and distributed delays. It first proves the existence and uniqueness of the balance point, then by employing the Lyapunov-Krasovskii functional and Young inequality, it gives the sufficient condition of global exponential stability of cellular neural network with mixed discrete and distributed delays, in addition, the example is provided to illustrate the applicability of the result.
基金Project supported by the Natural Science Foundation of the Higher Education Institutions of Jiangsu Province,Chinathe Foundation of Huaiyin Teachers College Professor,China(Grant Nos07KJD510027 and 06HSJS020)
文摘This paper presents a method used to the numeral eddy current sensor modelling based on the genetic neural network to settle its nonlinear problem. The principle and algorithms of genetic neural network are introduced. In this method, the nonlinear model parameters of the numeral eddy current sensor are optimized by genetic neural network （GNN） according to measurement data. So the method remains both the global searching ability of genetic algorithm and the good local searching ability of neural network. The nonlinear model has the advantages of strong robustness, on-line modelling and high precision. The maximum nonlinearity error can be reduced to 0.037% by using GNN. However, the maximum nonlinearity error is 0.075% using the least square method.
