Quantum error correction is a crucial technology for realizing quantum computers.These computers achieve faulttolerant quantum computing by detecting and correcting errors using decoding algorithms.Quantum error corre...Quantum error correction is a crucial technology for realizing quantum computers.These computers achieve faulttolerant quantum computing by detecting and correcting errors using decoding algorithms.Quantum error correction using neural network-based machine learning methods is a promising approach that is adapted to physical systems without the need to build noise models.In this paper,we use a distributed decoding strategy,which effectively alleviates the problem of exponential growth of the training set required for neural networks as the code distance of quantum error-correcting codes increases.Our decoding algorithm is based on renormalization group decoding and recurrent neural network decoder.The recurrent neural network is trained through the ResNet architecture to improve its decoding accuracy.Then we test the decoding performance of our distributed strategy decoder,recurrent neural network decoder,and the classic minimum weight perfect matching(MWPM)decoder for rotated surface codes with different code distances under the circuit noise model,the thresholds of these three decoders are about 0.0052,0.0051,and 0.0049,respectively.Our results demonstrate that the distributed strategy decoder outperforms the other two decoders,achieving approximately a 5%improvement in decoding efficiency compared to the MWPM decoder and approximately a 2%improvement compared to the recurrent neural network decoder.展开更多
This paper proposes a co-evolutionary recurrent neural network （CERNN） for the multi-step-prediction of chaotic time series, it estimates the proper parameters of phase space reconstruction and optimizes the structu...This paper proposes a co-evolutionary recurrent neural network （CERNN） for the multi-step-prediction of chaotic time series, it estimates the proper parameters of phase space reconstruction and optimizes the structure of recurrent neural networks by coevolutionary strategy. The searching space was separated into two subspaces and the individuals are trained in a parallel computational procedure. It can dynamically combine the embedding method with the capability of recurrent neural network to incorporate past experience due to internal recurrence. The effectiveness of CERNN is evaluated by using three benchmark chaotic time series data sets： the Lorenz series, Mackey-Glass series and real-world sun spot series. The simulation results show that CERNN improves the performances of multi-step-prediction of chaotic time series.展开更多
Early fault warning for nuclear power machinery is conducive to timely troubleshooting and reductions in safety risks and unnecessary costs. This paper presents a novel intelligent fault prediction method, integrated ...Early fault warning for nuclear power machinery is conducive to timely troubleshooting and reductions in safety risks and unnecessary costs. This paper presents a novel intelligent fault prediction method, integrated probabilistic principal component analysis(PPCA), multi-resolution wavelet analysis, Bayesian inference, and RNN model for nuclear power machinery that consider data uncertainty and chaotic time series. After denoising the source data, the Bayesian PPCA method is employed for dimensional reduction to obtain a refined data group. A recurrent neural network(RNN) prediction model is constructed, and a Bayesian statistical inference approach is developed to quantitatively assess the prediction reliability of the model. By modeling and analyzing the data collected on the steam turbine and components of a nuclear power plant, the results of the goodness of fit, mean square error distribution, and Bayesian confidence indicate that the proposed RNN model can implement early warning in the fault creep period. The accuracy and reliability of the proposed model are quantitatively verified.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
We propose a novel neural network based on a diagonal recurrent neural network and chaos, and its structure and learning algorithm are designed. The multilayer feedforward neural network, diagonal recurrent neural net...We propose a novel neural network based on a diagonal recurrent neural network and chaos, and its structure and learning algorithm are designed. The multilayer feedforward neural network, diagonal recurrent neural network, and chaotic diagonal recurrent neural network are used to approach the cubic symmetry map. The simulation results show that the approximation capability of the chaotic diagonal recurrent neural network is better than the other two neural networks.展开更多
The robust global exponential stability of a class of interval recurrent neural networks（RNNs） is studied,and a new robust stability criterion is obtained in the form of linear matrix inequality.The problem of robus...The robust global exponential stability of a class of interval recurrent neural networks（RNNs） is studied,and a new robust stability criterion is obtained in the form of linear matrix inequality.The problem of robust stability of interval RNNs is transformed into a problem of solving a class of linear matrix inequalities.Thus,the robust stability of interval RNNs can be analyzed by directly using the linear matrix inequalities（LMI） toolbox of MATLAB.Numerical example is given to show the effectiveness of the obtained results.展开更多
In this paper, we have improved delay-dependent stability criteria for recurrent neural networks with a delay varying over a range and Markovian jumping parameters. The criteria improve over some previous ones in that...In this paper, we have improved delay-dependent stability criteria for recurrent neural networks with a delay varying over a range and Markovian jumping parameters. The criteria improve over some previous ones in that they have fewer matrix variables yet less conservatism. In addition, a numerical example is provided to illustrate the applicability of the result using the linear matrix inequality toolbox in MATLAB.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
In this paper, the problem of delay-distribution-dependent stability is investigated for continuous-time recurrent neural networks （CRNNs） with stochastic delay. Different from the common assumptions on time delays,...In this paper, the problem of delay-distribution-dependent stability is investigated for continuous-time recurrent neural networks （CRNNs） with stochastic delay. Different from the common assumptions on time delays, it is assumed that the probability distribution of the delay taking values in some intervals is known a priori. By making full use of the information concerning the probability distribution of the delay and by using a tighter bounding technique （the reciprocally convex combination method）, less conservative asymptotic mean-square stable sufficient conditions are derived in terms of linear matrix inequalities （LMIs）. Two numerical examples show that our results are better than the existing ones.展开更多
Identification simulation for dynamical system which is based on genetic algorithm (GA) and recurrent multilayer neural network (RMNN) is presented. In order to reduce the inputs of the model, RMNN which can remember ...Identification simulation for dynamical system which is based on genetic algorithm (GA) and recurrent multilayer neural network (RMNN) is presented. In order to reduce the inputs of the model, RMNN which can remember and store some previous parameters is used for identifier. And for its high efficiency and optimization, genetic algorithm is introduced into training RMNN. Simulation results show the effectiveness of the proposed scheme. Under the same training algorithm, the identification performance of RMNN is superior to that of nonrecurrent multilayer neural network (NRMNN).展开更多
A scheme of adaptive control based on a recurrent neural network with a neural network compensation is presented for a class of nonlinear systems with a nonlinear prefix. The recurrent neural network is used to identi...A scheme of adaptive control based on a recurrent neural network with a neural network compensation is presented for a class of nonlinear systems with a nonlinear prefix. The recurrent neural network is used to identify the unknown nonlinear part and compensate the difference between the real output and the identified model output. The identified model of the controlled object consists of a linear model and the neural network. The generalized minimum variance control method is used to identify parameters, which can deal with the problem of adaptive control of systems with unknown nonlinear part, which can not be controlled by traditional methods. Simulation results show that this algorithm has higher precision, faster convergent speed.展开更多
This work proposes a recorded recurrent twin delayed deep deterministic(RRTD3)policy gradient algorithm to solve the challenge of constructing guidance laws for intercepting endoatmospheric maneuvering missiles with u...This work proposes a recorded recurrent twin delayed deep deterministic(RRTD3)policy gradient algorithm to solve the challenge of constructing guidance laws for intercepting endoatmospheric maneuvering missiles with uncertainties and observation noise.The attack-defense engagement scenario is modeled as a partially observable Markov decision process(POMDP).Given the benefits of recurrent neural networks(RNNs)in processing sequence information,an RNN layer is incorporated into the agent’s policy network to alleviate the bottleneck of traditional deep reinforcement learning methods while dealing with POMDPs.The measurements from the interceptor’s seeker during each guidance cycle are combined into one sequence as the input to the policy network since the detection frequency of an interceptor is usually higher than its guidance frequency.During training,the hidden states of the RNN layer in the policy network are recorded to overcome the partially observable problem that this RNN layer causes inside the agent.The training curves show that the proposed RRTD3 successfully enhances data efficiency,training speed,and training stability.The test results confirm the advantages of the RRTD3-based guidance laws over some conventional guidance laws.展开更多
With the popularity of smart handheld devices, mobile streaming video has multiplied the global network traffic in recent years. A huge concern of users' quality of experience(Qo E) has made rate adaptation method...With the popularity of smart handheld devices, mobile streaming video has multiplied the global network traffic in recent years. A huge concern of users' quality of experience(Qo E) has made rate adaptation methods very attractive. In this paper, we propose a two-phase rate adaptation strategy to improve users' real-time video Qo E. First, to measure and assess video Qo E, we provide a continuous Qo E prediction engine modeled by RNN recurrent neural network. Different from traditional Qo E models which consider the Qo E-aware factors separately or incompletely, our RNN-Qo E model accounts for three descriptive factors(video quality, rebuffering, and rate change) and reflects the impact of cognitive memory and recency. Besides, the video playing is separated into the initial startup phase and the steady playback phase, and we takes different optimization goals for each phase: the former aims at shortening the startup delay while the latter ameliorates the video quality and the rebufferings. Simulation results have shown that RNN-Qo E can follow the subjective Qo E quite well, and the proposed strategy can effectively reduce the occurrence of rebufferings caused by the mismatch between the requested video rates and the fluctuated throughput and attains standout performance on real-time Qo E compared with classical rate adaption methods.展开更多
Multiple stability for two-dimensional delayed recurrent neural networks with piecewise linear activation flmctions of 2r （r 〉 1） corner points is studied. Sufficient conditions are established for checking the exi...Multiple stability for two-dimensional delayed recurrent neural networks with piecewise linear activation flmctions of 2r （r 〉 1） corner points is studied. Sufficient conditions are established for checking the existence of （2r ＋ 1）2 equilibria in delayed recurrent neural networks. Under these conditions, （r ＋ 1）2 equilibria are locally exponentially stable, and （2r＋ 1）2 -（r ＋ 1）2 -r2 equilibria are unstable. Attractive basins of stable equilibria are estimated, which are larger than invariant sets derived by decomposing state space. One example is provided to illustrate the effectiveness of our results.展开更多
The estimation of state of charge(SOC)using deep neural networks(DNN)generally requires a considerable number of labelled samples for training,which refer to the current and voltage pieces with knowing their correspon...The estimation of state of charge(SOC)using deep neural networks(DNN)generally requires a considerable number of labelled samples for training,which refer to the current and voltage pieces with knowing their corresponding SOCs.However,the collection of labelled samples is costly and time-consuming.In contrast,the unlabelled training samples,which consist of the current and voltage data with unknown SOCs,are easy to obtain.In view of this,this paper proposes an improved DNN for SOC estimation by effectively using both a pool of unlabelled samples and a limited number of labelled samples.Besides the traditional supervised network,the proposed method uses an input reconstruction network to reformulate the time dependency features of the voltage and current.In this way,the developed network can extract useful information from the unlabelled samples.The proposed method is validated under different drive cycles and temperature conditions.The results reveal that the SOC estimation accuracy of the DNN trained with both labelled and unlabelled samples outperforms that of only using a limited number of labelled samples.In addition,when the dataset with reduced number of labelled samples to some extent is used to test the developed network,it is found that the proposed method performs well and is robust in producing the model outputs with the required accuracy when the unlabelled samples are involved in the model training.Furthermore,the proposed method is evaluated with different recurrent neural networks(RNNs)applied to the input reconstruction module.The results indicate that the proposed method is feasible for various RNN algorithms,and it could be flexibly applied to other conditions as required.展开更多
Purpose:With more and more digital collections of various information resources becoming available,also increasing is the challenge of assigning subject index terms and classes from quality knowledge organization syst...Purpose:With more and more digital collections of various information resources becoming available,also increasing is the challenge of assigning subject index terms and classes from quality knowledge organization systems.While the ultimate purpose is to understand the value of automatically produced Dewey Decimal Classification(DDC)classes for Swedish digital collections,the paper aims to evaluate the performance of six machine learning algorithms as well as a string-matching algorithm based on characteristics of DDC.Design/methodology/approach:State-of-the-art machine learning algorithms require at least 1,000 training examples per class.The complete data set at the time of research involved 143,838 records which had to be reduced to top three hierarchical levels of DDC in order to provide sufficient training data(totaling 802 classes in the training and testing sample,out of 14,413 classes at all levels).Findings:Evaluation shows that Support Vector Machine with linear kernel outperforms other machine learning algorithms as well as the string-matching algorithm on average;the string-matching algorithm outperforms machine learning for specific classes when characteristics of DDC are most suitable for the task.Word embeddings combined with different types of neural networks(simple linear network,standard neural network,1 D convolutional neural network,and recurrent neural network)produced worse results than Support Vector Machine,but reach close results,with the benefit of a smaller representation size.Impact of features in machine learning shows that using keywords or combining titles and keywords gives better results than using only titles as input.Stemming only marginally improves the results.Removed stop-words reduced accuracy in most cases,while removing less frequent words increased it marginally.The greatest impact is produced by the number of training examples:81.90%accuracy on the training set is achieved when at least 1,000 records per class are available in the training set,and 66.13%when too few records(often less than A Comparison of Approaches100 per class)on which to train are available—and these hold only for top 3 hierarchical levels(803 instead of 14,413 classes).Research limitations:Having to reduce the number of hierarchical levels to top three levels of DDC because of the lack of training data for all classes,skews the results so that they work in experimental conditions but barely for end users in operational retrieval systems.Practical implications:In conclusion,for operative information retrieval systems applying purely automatic DDC does not work,either using machine learning(because of the lack of training data for the large number of DDC classes)or using string-matching algorithm(because DDC characteristics perform well for automatic classification only in a small number of classes).Over time,more training examples may become available,and DDC may be enriched with synonyms in order to enhance accuracy of automatic classification which may also benefit information retrieval performance based on DDC.In order for quality information services to reach the objective of highest possible precision and recall,automatic classification should never be implemented on its own;instead,machine-aided indexing that combines the efficiency of automatic suggestions with quality of human decisions at the final stage should be the way for the future.Originality/value:The study explored machine learning on a large classification system of over 14,000 classes which is used in operational information retrieval systems.Due to lack of sufficient training data across the entire set of classes,an approach complementing machine learning,that of string matching,was applied.This combination should be explored further since it provides the potential for real-life applications with large target classification systems.展开更多
At present, there has been an increasing interest in neuron-fuzzy systems, the combinations of artificial neural networks with fuzzy logic. In this paper, a definition of fuzzy finite state automata （FFA） is introdu...At present, there has been an increasing interest in neuron-fuzzy systems, the combinations of artificial neural networks with fuzzy logic. In this paper, a definition of fuzzy finite state automata （FFA） is introduced and fuzzy knowledge equivalence representations between neural networks, fuzzy systems and models of automata are discussed. Once the network has been trained, we develop a method to extract a representation of the FFA encoded in the recurrent neural network that recognizes the training rules.展开更多
Landslide displacement prediction can enhance the efficacy of landslide monitoring system,and the prediction of the periodic displacement is particularly challenging.In the previous studies,static regression models(e....Landslide displacement prediction can enhance the efficacy of landslide monitoring system,and the prediction of the periodic displacement is particularly challenging.In the previous studies,static regression models(e.g.,support vector machine(SVM))were mostly used for predicting the periodic displacement.These models may have bad performances,when the dynamic features of landslide triggers are incorporated.This paper proposes a method for predicting the landslide displacement in a dynamic manner,based on the gated recurrent unit(GRU)neural network and complete ensemble empirical decomposition with adaptive noise(CEEMDAN).The CEEMDAN is used to decompose the training data,and the GRU is subsequently used for predicting the periodic displacement.Implementation procedures of the proposed method were illustrated by a case study in the Caojiatuo landslide area,and SVM was also adopted for the periodic displacement prediction.This case study shows that the predictors obtained by SVM are inaccurate,as the landslide displacement is in a pronouncedly step-wise manner.By contrast,the accuracy can be significantly improved using the dynamic predictive method.This paper reveals the significance of capturing the dynamic features of the inputs in the training process,when the machine learning models are adopted to predict the landslide displacement.展开更多
基金Project supported by Natural Science Foundation of Shandong Province,China (Grant Nos.ZR2021MF049,ZR2022LLZ012,and ZR2021LLZ001)。
文摘Quantum error correction is a crucial technology for realizing quantum computers.These computers achieve faulttolerant quantum computing by detecting and correcting errors using decoding algorithms.Quantum error correction using neural network-based machine learning methods is a promising approach that is adapted to physical systems without the need to build noise models.In this paper,we use a distributed decoding strategy,which effectively alleviates the problem of exponential growth of the training set required for neural networks as the code distance of quantum error-correcting codes increases.Our decoding algorithm is based on renormalization group decoding and recurrent neural network decoder.The recurrent neural network is trained through the ResNet architecture to improve its decoding accuracy.Then we test the decoding performance of our distributed strategy decoder,recurrent neural network decoder,and the classic minimum weight perfect matching(MWPM)decoder for rotated surface codes with different code distances under the circuit noise model,the thresholds of these three decoders are about 0.0052,0.0051,and 0.0049,respectively.Our results demonstrate that the distributed strategy decoder outperforms the other two decoders,achieving approximately a 5%improvement in decoding efficiency compared to the MWPM decoder and approximately a 2%improvement compared to the recurrent neural network decoder.
基金Project supported by the State Key Program of National Natural Science of China (Grant No 30230350)the Natural Science Foundation of Guangdong Province,China (Grant No 07006474)
文摘This paper proposes a co-evolutionary recurrent neural network （CERNN） for the multi-step-prediction of chaotic time series, it estimates the proper parameters of phase space reconstruction and optimizes the structure of recurrent neural networks by coevolutionary strategy. The searching space was separated into two subspaces and the individuals are trained in a parallel computational procedure. It can dynamically combine the embedding method with the capability of recurrent neural network to incorporate past experience due to internal recurrence. The effectiveness of CERNN is evaluated by using three benchmark chaotic time series data sets： the Lorenz series, Mackey-Glass series and real-world sun spot series. The simulation results show that CERNN improves the performances of multi-step-prediction of chaotic time series.
基金the National Natural Science Foundation of China(No.51875209)the Guangdong Basic and Applied Basic Research Foundation(No.2019B1515120060)the Open Funds of State Key Laboratory of Nuclear Power Safety Monitoring Technology and Equipment。
文摘Early fault warning for nuclear power machinery is conducive to timely troubleshooting and reductions in safety risks and unnecessary costs. This paper presents a novel intelligent fault prediction method, integrated probabilistic principal component analysis(PPCA), multi-resolution wavelet analysis, Bayesian inference, and RNN model for nuclear power machinery that consider data uncertainty and chaotic time series. After denoising the source data, the Bayesian PPCA method is employed for dimensional reduction to obtain a refined data group. A recurrent neural network(RNN) prediction model is constructed, and a Bayesian statistical inference approach is developed to quantitatively assess the prediction reliability of the model. By modeling and analyzing the data collected on the steam turbine and components of a nuclear power plant, the results of the goodness of fit, mean square error distribution, and Bayesian confidence indicate that the proposed RNN model can implement early warning in the fault creep period. The accuracy and reliability of the proposed model are quantitatively verified.
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.
基金Project supported by the National Natural Science Foundation of China (Grant Nos. 61173183,60973152,and 60573172)the Superior University Doctor Subject Special Scientific Research Foundation of China (Grant No. 20070141014)the Natural Science Foundation of Liaoning Province,China (Grant No. 20082165)
文摘We propose a novel neural network based on a diagonal recurrent neural network and chaos, and its structure and learning algorithm are designed. The multilayer feedforward neural network, diagonal recurrent neural network, and chaotic diagonal recurrent neural network are used to approach the cubic symmetry map. The simulation results show that the approximation capability of the chaotic diagonal recurrent neural network is better than the other two neural networks.
基金Supported by the Natural Science Foundation of Shandong Province (ZR2010FM038,ZR2010FL017)
文摘The robust global exponential stability of a class of interval recurrent neural networks（RNNs） is studied,and a new robust stability criterion is obtained in the form of linear matrix inequality.The problem of robust stability of interval RNNs is transformed into a problem of solving a class of linear matrix inequalities.Thus,the robust stability of interval RNNs can be analyzed by directly using the linear matrix inequalities（LMI） toolbox of MATLAB.Numerical example is given to show the effectiveness of the obtained results.
基金Project supported by the National Natural Science Foundation of China (Grant No.60674026)the Jiangsu Provincial Natural Science Foundation of China (Grant No.BK2007016)
文摘In this paper, we have improved delay-dependent stability criteria for recurrent neural networks with a delay varying over a range and Markovian jumping parameters. The criteria improve over some previous ones in that they have fewer matrix variables yet less conservatism. In addition, a numerical example is provided to illustrate the applicability of the result using the linear matrix inequality toolbox in MATLAB.
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.61273164,61034005,and 60974071)the National High Technology Research and Development Program of China(Grant No.2012AA040104)the Fundamental Research Funds for the Central Universities(Grant Nos.N100104102 and N110604007)
文摘In this paper, the problem of delay-distribution-dependent stability is investigated for continuous-time recurrent neural networks （CRNNs） with stochastic delay. Different from the common assumptions on time delays, it is assumed that the probability distribution of the delay taking values in some intervals is known a priori. By making full use of the information concerning the probability distribution of the delay and by using a tighter bounding technique （the reciprocally convex combination method）, less conservative asymptotic mean-square stable sufficient conditions are derived in terms of linear matrix inequalities （LMIs）. Two numerical examples show that our results are better than the existing ones.
文摘Identification simulation for dynamical system which is based on genetic algorithm (GA) and recurrent multilayer neural network (RMNN) is presented. In order to reduce the inputs of the model, RMNN which can remember and store some previous parameters is used for identifier. And for its high efficiency and optimization, genetic algorithm is introduced into training RMNN. Simulation results show the effectiveness of the proposed scheme. Under the same training algorithm, the identification performance of RMNN is superior to that of nonrecurrent multilayer neural network (NRMNN).
文摘A scheme of adaptive control based on a recurrent neural network with a neural network compensation is presented for a class of nonlinear systems with a nonlinear prefix. The recurrent neural network is used to identify the unknown nonlinear part and compensate the difference between the real output and the identified model output. The identified model of the controlled object consists of a linear model and the neural network. The generalized minimum variance control method is used to identify parameters, which can deal with the problem of adaptive control of systems with unknown nonlinear part, which can not be controlled by traditional methods. Simulation results show that this algorithm has higher precision, faster convergent speed.
基金supported by the National Natural Science Foundation of China(Grant No.12072090)。
文摘This work proposes a recorded recurrent twin delayed deep deterministic(RRTD3)policy gradient algorithm to solve the challenge of constructing guidance laws for intercepting endoatmospheric maneuvering missiles with uncertainties and observation noise.The attack-defense engagement scenario is modeled as a partially observable Markov decision process(POMDP).Given the benefits of recurrent neural networks(RNNs)in processing sequence information,an RNN layer is incorporated into the agent’s policy network to alleviate the bottleneck of traditional deep reinforcement learning methods while dealing with POMDPs.The measurements from the interceptor’s seeker during each guidance cycle are combined into one sequence as the input to the policy network since the detection frequency of an interceptor is usually higher than its guidance frequency.During training,the hidden states of the RNN layer in the policy network are recorded to overcome the partially observable problem that this RNN layer causes inside the agent.The training curves show that the proposed RRTD3 successfully enhances data efficiency,training speed,and training stability.The test results confirm the advantages of the RRTD3-based guidance laws over some conventional guidance laws.
基金supported by the National Nature Science Foundation of China(NSFC 60622110,61471220,91538107,91638205)National Basic Research Project of China(973,2013CB329006),GY22016058
文摘With the popularity of smart handheld devices, mobile streaming video has multiplied the global network traffic in recent years. A huge concern of users' quality of experience(Qo E) has made rate adaptation methods very attractive. In this paper, we propose a two-phase rate adaptation strategy to improve users' real-time video Qo E. First, to measure and assess video Qo E, we provide a continuous Qo E prediction engine modeled by RNN recurrent neural network. Different from traditional Qo E models which consider the Qo E-aware factors separately or incompletely, our RNN-Qo E model accounts for three descriptive factors(video quality, rebuffering, and rate change) and reflects the impact of cognitive memory and recency. Besides, the video playing is separated into the initial startup phase and the steady playback phase, and we takes different optimization goals for each phase: the former aims at shortening the startup delay while the latter ameliorates the video quality and the rebufferings. Simulation results have shown that RNN-Qo E can follow the subjective Qo E quite well, and the proposed strategy can effectively reduce the occurrence of rebufferings caused by the mismatch between the requested video rates and the fluctuated throughput and attains standout performance on real-time Qo E compared with classical rate adaption methods.
基金Project supported by the National Natural Science Foundation of China (Grant Nos. 50977008, 61034005, and 61074073)the National Basic Research Program of China (Grant No. 2009CB320601)+1 种基金the Program for New Century Excellent Talents in Universities of China (Grant No. NCET-10-0306)the Fundamental Research Funds for the Central Universities of China(Grant Nos. N110604005 and N110504001)
文摘Multiple stability for two-dimensional delayed recurrent neural networks with piecewise linear activation flmctions of 2r （r 〉 1） corner points is studied. Sufficient conditions are established for checking the existence of （2r ＋ 1）2 equilibria in delayed recurrent neural networks. Under these conditions, （r ＋ 1）2 equilibria are locally exponentially stable, and （2r＋ 1）2 -（r ＋ 1）2 -r2 equilibria are unstable. Attractive basins of stable equilibria are estimated, which are larger than invariant sets derived by decomposing state space. One example is provided to illustrate the effectiveness of our results.
基金the financial support from the China Scholarship Council(CSC)(No.202207550010)。
文摘The estimation of state of charge(SOC)using deep neural networks(DNN)generally requires a considerable number of labelled samples for training,which refer to the current and voltage pieces with knowing their corresponding SOCs.However,the collection of labelled samples is costly and time-consuming.In contrast,the unlabelled training samples,which consist of the current and voltage data with unknown SOCs,are easy to obtain.In view of this,this paper proposes an improved DNN for SOC estimation by effectively using both a pool of unlabelled samples and a limited number of labelled samples.Besides the traditional supervised network,the proposed method uses an input reconstruction network to reformulate the time dependency features of the voltage and current.In this way,the developed network can extract useful information from the unlabelled samples.The proposed method is validated under different drive cycles and temperature conditions.The results reveal that the SOC estimation accuracy of the DNN trained with both labelled and unlabelled samples outperforms that of only using a limited number of labelled samples.In addition,when the dataset with reduced number of labelled samples to some extent is used to test the developed network,it is found that the proposed method performs well and is robust in producing the model outputs with the required accuracy when the unlabelled samples are involved in the model training.Furthermore,the proposed method is evaluated with different recurrent neural networks(RNNs)applied to the input reconstruction module.The results indicate that the proposed method is feasible for various RNN algorithms,and it could be flexibly applied to other conditions as required.
文摘Purpose:With more and more digital collections of various information resources becoming available,also increasing is the challenge of assigning subject index terms and classes from quality knowledge organization systems.While the ultimate purpose is to understand the value of automatically produced Dewey Decimal Classification(DDC)classes for Swedish digital collections,the paper aims to evaluate the performance of six machine learning algorithms as well as a string-matching algorithm based on characteristics of DDC.Design/methodology/approach:State-of-the-art machine learning algorithms require at least 1,000 training examples per class.The complete data set at the time of research involved 143,838 records which had to be reduced to top three hierarchical levels of DDC in order to provide sufficient training data(totaling 802 classes in the training and testing sample,out of 14,413 classes at all levels).Findings:Evaluation shows that Support Vector Machine with linear kernel outperforms other machine learning algorithms as well as the string-matching algorithm on average;the string-matching algorithm outperforms machine learning for specific classes when characteristics of DDC are most suitable for the task.Word embeddings combined with different types of neural networks(simple linear network,standard neural network,1 D convolutional neural network,and recurrent neural network)produced worse results than Support Vector Machine,but reach close results,with the benefit of a smaller representation size.Impact of features in machine learning shows that using keywords or combining titles and keywords gives better results than using only titles as input.Stemming only marginally improves the results.Removed stop-words reduced accuracy in most cases,while removing less frequent words increased it marginally.The greatest impact is produced by the number of training examples:81.90%accuracy on the training set is achieved when at least 1,000 records per class are available in the training set,and 66.13%when too few records(often less than A Comparison of Approaches100 per class)on which to train are available—and these hold only for top 3 hierarchical levels(803 instead of 14,413 classes).Research limitations:Having to reduce the number of hierarchical levels to top three levels of DDC because of the lack of training data for all classes,skews the results so that they work in experimental conditions but barely for end users in operational retrieval systems.Practical implications:In conclusion,for operative information retrieval systems applying purely automatic DDC does not work,either using machine learning(because of the lack of training data for the large number of DDC classes)or using string-matching algorithm(because DDC characteristics perform well for automatic classification only in a small number of classes).Over time,more training examples may become available,and DDC may be enriched with synonyms in order to enhance accuracy of automatic classification which may also benefit information retrieval performance based on DDC.In order for quality information services to reach the objective of highest possible precision and recall,automatic classification should never be implemented on its own;instead,machine-aided indexing that combines the efficiency of automatic suggestions with quality of human decisions at the final stage should be the way for the future.Originality/value:The study explored machine learning on a large classification system of over 14,000 classes which is used in operational information retrieval systems.Due to lack of sufficient training data across the entire set of classes,an approach complementing machine learning,that of string matching,was applied.This combination should be explored further since it provides the potential for real-life applications with large target classification systems.
基金Youth Science and Technology Foundation of Sichuan (No. L080011YF021104)
文摘At present, there has been an increasing interest in neuron-fuzzy systems, the combinations of artificial neural networks with fuzzy logic. In this paper, a definition of fuzzy finite state automata （FFA） is introduced and fuzzy knowledge equivalence representations between neural networks, fuzzy systems and models of automata are discussed. Once the network has been trained, we develop a method to extract a representation of the FFA encoded in the recurrent neural network that recognizes the training rules.
基金The authors appreciate the financial support provided by the Natural Science Foundation of China(No.41807294)This study was also financially supported by China Geological Survey Project(Nos.DD20190716 and 0001212020CC60002)。
文摘Landslide displacement prediction can enhance the efficacy of landslide monitoring system,and the prediction of the periodic displacement is particularly challenging.In the previous studies,static regression models(e.g.,support vector machine(SVM))were mostly used for predicting the periodic displacement.These models may have bad performances,when the dynamic features of landslide triggers are incorporated.This paper proposes a method for predicting the landslide displacement in a dynamic manner,based on the gated recurrent unit(GRU)neural network and complete ensemble empirical decomposition with adaptive noise(CEEMDAN).The CEEMDAN is used to decompose the training data,and the GRU is subsequently used for predicting the periodic displacement.Implementation procedures of the proposed method were illustrated by a case study in the Caojiatuo landslide area,and SVM was also adopted for the periodic displacement prediction.This case study shows that the predictors obtained by SVM are inaccurate,as the landslide displacement is in a pronouncedly step-wise manner.By contrast,the accuracy can be significantly improved using the dynamic predictive method.This paper reveals the significance of capturing the dynamic features of the inputs in the training process,when the machine learning models are adopted to predict the landslide displacement.
