Bayesian regularized BP neural network（BRBPNN） technique was applied in the chlorophyll-α prediction of Nanzui water area in Dongting Lake. Through BP network interpolation method, the input and output samples of t...Bayesian regularized BP neural network（BRBPNN） technique was applied in the chlorophyll-α prediction of Nanzui water area in Dongting Lake. Through BP network interpolation method, the input and output samples of the network were obtained. After the selection of input variables using stepwise/multiple linear regression method in SPSS i1.0 software, the BRBPNN model was established between chlorophyll-α and environmental parameters, biological parameters. The achieved optimal network structure was 3-11-1 with the correlation coefficients and the mean square errors for the training set and the test set as 0.999 and 0.000？8426, 0.981 and 0.0216 respectively. The sum of square weights between each input neuron and the hidden layer of optimal BRBPNN models of different structures indicated that the effect of individual input parameter on chlorophyll- α declined in the order of alga amount 〉 secchi disc depth（SD） 〉 electrical conductivity （EC）. Additionally, it also demonstrated that the contributions of these three factors were the maximal for the change of chlorophyll-α concentration, total phosphorus（TP） and total nitrogen（TN） were the minimal. All the results showed that BRBPNN model was capable of automated regularization parameter selection and thus it may ensure the excellent generation ability and robustness. Thus, this study laid the foundation for the application of BRBPNN model in the analysis of aquatic ecological data（chlorophyll-α prediction） and the explanation about the effective eutrophication treatment measures for Nanzui water area in Dongting Lake.展开更多
Four layer feedforward regular fuzzy neural networks are constructed. Universal approximations to some continuous fuzzy functions defined on F 0 (R) n by the four layer fuzzy neural networks are shown. At f...Four layer feedforward regular fuzzy neural networks are constructed. Universal approximations to some continuous fuzzy functions defined on F 0 (R) n by the four layer fuzzy neural networks are shown. At first,multivariate Bernstein polynomials associated with fuzzy valued functions are empolyed to approximate continuous fuzzy valued functions defined on each compact set of R n . Secondly,by introducing cut preserving fuzzy mapping,the equivalent conditions for continuous fuzzy functions that can be arbitrarily closely approximated by regular fuzzy neural networks are shown. Finally a few of sufficient and necessary conditions for characterizing approximation capabilities of regular fuzzy neural networks are obtained. And some concrete fuzzy functions demonstrate our conclusions.展开更多
A neural network with a feed forward topology and Bayesian regularization training algorithm is used to predict the austenite formation temperatures （At1 and A13） by considering the percentage of alloying elements i...A neural network with a feed forward topology and Bayesian regularization training algorithm is used to predict the austenite formation temperatures （At1 and A13） by considering the percentage of alloying elements in chemical composition of steel. The data base used here involves a large variety of different steel types such as struc- tural steels, stainless steels, rail steels, spring steels, high temperature creep resisting steels and tool steels. Scatter diagrams and mean relative error （MRE） statistical criteria are used to compare the performance of developed neural network with the results of Andrew% empirical equations and a feed forward neural network with ＂gradient descent with momentum＂ training algorithm. The results showed that Bayesian regularization neural network has the best performance. Also, due to the satisfactory results of the developed neural network, it was used to investigate the effect of the chemical composition on Ac1 and At3 temperatures. Results are in accordance with materials science theories.展开更多
By defining fuzzy valued simple functions and giving L1(μ) approximations of fuzzy valued integrably bounded functions by such simple functions, the paper analyses by L1(μ)-norm the approximation capability of four-...By defining fuzzy valued simple functions and giving L1(μ) approximations of fuzzy valued integrably bounded functions by such simple functions, the paper analyses by L1(μ)-norm the approximation capability of four-layer feedforward regular fuzzy neural networks to the fuzzy valued integrably bounded function F : Rn → FcO(R). That is, if the transfer functionσ: R→R is non-polynomial and integrable function on each finite interval, F may be innorm approximated by fuzzy valued functions defined as to anydegree of accuracy. Finally some real examples demonstrate the conclusions.展开更多
The regular small-world network, which contains the properties of small-world network and regular network, has recently received substantial attention and has been applied in researches on 2-person games. However, it ...The regular small-world network, which contains the properties of small-world network and regular network, has recently received substantial attention and has been applied in researches on 2-person games. However, it is a common phenomenon that cooperation always appears as a group behavior. In order to investigate the mechanism of group cooperation, we propose an evolutionary multi-person game model on a regular small-world network based on public goods game theory. Then, to make a comparison of frequency of cooperation among different networks, we carry out simulations on three kinds of networks with the same configuration of average degree： the square lattice, regular small-world network and random regular network. The results of simulation show that the group cooperation will emerge among these three networks when the enhancement factor r exceeds a threshold. Furthermore, time required for full cooperation on regular small-world network is slightly longer than the other networks, which indicates that the compact interactions and random interactions will promote cooperation, while the longer-range links are the obstacles in the emergence of cooperation. In addition, the cooperation would be promoted further by enhancing the random interactions on regular small-world network.展开更多
We investigate the synchronization ability of four types of regular coupled networks. By introducing the proper error variables and Lyapunov functions, we turn the stability of synchronization manifold into that of nu...We investigate the synchronization ability of four types of regular coupled networks. By introducing the proper error variables and Lyapunov functions, we turn the stability of synchronization manifold into that of null solution of error equations, further, into the negative definiteness of some symmetric matrices, thus we get the sufficient synchronization stability conditions. To test the valid of the results, we take the Chua's circuit as an example. Although the theoretical synchronization thresholds appear to be very conservative, they provide new insights about the influence of topology and scale of networks on synchronization, and that the theoretical results and our numerical simulations are consistent.展开更多
Spiking regularity in a clustered Hodgkin–Huxley（HH） neuronal network has been studied in this letter. A stochastic HH neuronal model with channel blocks has been applied as local neuronal model. Effects of the int...Spiking regularity in a clustered Hodgkin–Huxley（HH） neuronal network has been studied in this letter. A stochastic HH neuronal model with channel blocks has been applied as local neuronal model. Effects of the internal channel noise on the spiking regularity are discussed by changing the membrane patch size. We find that when there is no channel blocks in potassium channels, there exist some intermediate membrane patch sizes at which the spiking regularity could reach to a higher level. Spiking regularity increases with the membrane patch size when sodium channels are not blocked. Namely, depending on different channel blocking states, internal channel noise tuned by membrane patch size could have different influence on the spiking regularity of neuronal networks.展开更多
A method for fast 1-fold cross validation is proposed for the regularized extreme learning machine （RELM）. The computational time of fast l-fold cross validation increases as the fold number decreases, which is oppo...A method for fast 1-fold cross validation is proposed for the regularized extreme learning machine （RELM）. The computational time of fast l-fold cross validation increases as the fold number decreases, which is opposite to that of naive 1-fold cross validation. As opposed to naive l-fold cross validation, fast l-fold cross validation takes the advantage in terms of computational time, especially for the large fold number such as l 〉 20. To corroborate the efficacy and feasibility of fast l-fold cross validation, experiments on five benchmark regression data sets are evaluated.展开更多
We consider the problem of minimizing a block separable convex function(possibly nondifferentiable, and including constraints) plus Laplacian regularization, a problem that arises in applications including model fitti...We consider the problem of minimizing a block separable convex function(possibly nondifferentiable, and including constraints) plus Laplacian regularization, a problem that arises in applications including model fitting, regularizing stratified models, and multi-period portfolio optimization. We develop a distributed majorization-minimization method for this general problem, and derive a complete, self-contained, general,and simple proof of convergence. Our method is able to scale to very large problems, and we illustrate our approach on two applications, demonstrating its scalability and accuracy.展开更多
As a major component of speech signal processing, speech emotion recognition has become increasingly essential to understanding human communication. Benefitting from deep learning, many researchers have proposed vario...As a major component of speech signal processing, speech emotion recognition has become increasingly essential to understanding human communication. Benefitting from deep learning, many researchers have proposed various unsupervised models to extract effective emotional features and supervised models to train emotion recognition systems. In this paper, we utilize semi-supervised ladder networks for speech emotion recognition. The model is trained by minimizing the supervised loss and auxiliary unsupervised cost function. The addition of the unsupervised auxiliary task provides powerful discriminative representations of the input features, and is also regarded as the regularization of the emotional supervised task. We also compare the ladder network with other classical autoencoder structures. The experiments were conducted on the interactive emotional dyadic motion capture (IEMOCAP) database, and the results reveal that the proposed methods achieve superior performance with a small number of labelled data and achieves better performance than other methods.展开更多
Topological indices enable to gather information for the underlying topology of chemical structures and networks.Novel harmonic indices have been defined recently.All degree based topological indices are defined by us...Topological indices enable to gather information for the underlying topology of chemical structures and networks.Novel harmonic indices have been defined recently.All degree based topological indices are defined by using the classical degree concept.Recently two novel degree concept have been defined in graph theory:ve-degree and evdegree.Ve-degree Zagreb indices have been defined by using ve-degree concept.The prediction power of the ve-degree Zagreb indices is stronger than the classical Zagreb indices.Dominating oxide,silicate and oxygen networks are important network models in view of chemistry,physics and information science.Physical and mathematical properties of dominating oxide,silicate and oxygen networks have been considerably studied in graph theory and network theory.Topological properties of the dominating oxide,silicate and oxygen networks have been intensively investigated for the last few years period.In this study we examined,the first,the fifth harmonic and ev-degree topological indices of dominating oxide(DOX),regular triangulene oxide network(RTOX)and dominating silicate network(DSL).展开更多
This article presents two new kinds of artificial neural network （ANN） response surface methods （RSMs）： the ANN RSM based on early stopping technique （ANNRSM-1）, and the ANN RSM based on regularization theory ...This article presents two new kinds of artificial neural network （ANN） response surface methods （RSMs）： the ANN RSM based on early stopping technique （ANNRSM-1）, and the ANN RSM based on regularization theory （ANNRSM-2）. The following improvements are made to the conventional ANN RSM （ANNRSM-0）： 1） by monitoring the validation error during the training process, ANNRSM-1 determines the early stopping point and the training stopping point, and the weight vector at the early stopping point, which corresponds to the ANN model with the optimal generalization, is finally returned as the training result; 2） according to the regularization theory, ANNRSM-2 modifies the conventional training performance function by adding to it the sum of squares of the network weights, so the network weights are forced to have smaller values while the training error decreases. Tests show that the performance of ANN RSM becomes much better due to the above-mentioned improvements： first, ANNRSM-1 and ANNRSM-2 approximate to the limit state function （LSF） more accurately than ANNRSM-0; second, the estimated failure probabilities given by ANNRSM-1 and ANNRSM-2 have smaller errors than that obtained by ANNRSM-0; third, compared with ANNRSM-0, ANNRSM-1 and ANNRSM-2 require much fewer data samples to achieve stable failure probability results.展开更多
This paper investigates the Morgan＇s problem of Boolean control networks. Based on the matrix expression of logical functions, two key steps are proposed to solve the problem. First, the Boolean control network is co...This paper investigates the Morgan＇s problem of Boolean control networks. Based on the matrix expression of logical functions, two key steps are proposed to solve the problem. First, the Boolean control network is converted into an output- decomposed form by constructing a set of consistent outputfriendly subspaces, and a necessary and sufficient condition for the existence of the consistent output-friendly subspaces is obtained. Secondly, a type of state feedback controllers are designed to solve the Morgan＇s problem if it is solvable. By solving a set of matrix equations, a necessary and sufficient condition for converting an output-decomposed form to an input-output decomposed form is given, and by verifying the output controllability matrix, the solvability of Morgan＇s problem is obtained.展开更多
We construct a complete-connective regular network based on Self-replication Space and the structural principles of cantor set and Koch curve. A new definition of dimension is proposed in the paper, and we also invest...We construct a complete-connective regular network based on Self-replication Space and the structural principles of cantor set and Koch curve. A new definition of dimension is proposed in the paper, and we also investigate a simplified method to calculate the dimension of two regular networks. By the study results, we can get a extension: the formation of Euclidean space may be built by the process of the Big Bang's continuously growing at a constant rate of three times.展开更多
This article is intended as a proposal for a numerical model for the prediction of the ultimate moment of a reinforced concrete beam reinforced with composite materials based on neural networks, which are classified i...This article is intended as a proposal for a numerical model for the prediction of the ultimate moment of a reinforced concrete beam reinforced with composite materials based on neural networks, which are classified in the artificial intelligence method. In this work, a RBF network or radial basis function type model was created and tested. The validation of the RBF architecture consists in judging its predictive capacity by using the weights and biases computed during the training, to apply them to another database which did not participate to the training and testing of the model. So, with Bayesian regularization, a maximum error of 0.0813 Tm in absolute value was found between the targets and predicted outputs. The value of the mean square error MSE = 1.1106 * 10<sup>-4</sup> allowed us to quantify and justify the prediction performance of this network. Through this article, RBF network model was justified perform and can be used and exploited by our engineers with a high reliability rate.展开更多
The aim of this paper is to broaden the application of Stochastic Configuration Network (SCN) in the semi-supervised domain by utilizing common unlabeled data in daily life. It can enhance the classification accuracy ...The aim of this paper is to broaden the application of Stochastic Configuration Network (SCN) in the semi-supervised domain by utilizing common unlabeled data in daily life. It can enhance the classification accuracy of decentralized SCN algorithms while effectively protecting user privacy. To this end, we propose a decentralized semi-supervised learning algorithm for SCN, called DMT-SCN, which introduces teacher and student models by combining the idea of consistency regularization to improve the response speed of model iterations. In order to reduce the possible negative impact of unsupervised data on the model, we purposely change the way of adding noise to the unlabeled data. Simulation results show that the algorithm can effectively utilize unlabeled data to improve the classification accuracy of SCN training and is robust under different ground simulation environments.展开更多
文摘Bayesian regularized BP neural network（BRBPNN） technique was applied in the chlorophyll-α prediction of Nanzui water area in Dongting Lake. Through BP network interpolation method, the input and output samples of the network were obtained. After the selection of input variables using stepwise/multiple linear regression method in SPSS i1.0 software, the BRBPNN model was established between chlorophyll-α and environmental parameters, biological parameters. The achieved optimal network structure was 3-11-1 with the correlation coefficients and the mean square errors for the training set and the test set as 0.999 and 0.000？8426, 0.981 and 0.0216 respectively. The sum of square weights between each input neuron and the hidden layer of optimal BRBPNN models of different structures indicated that the effect of individual input parameter on chlorophyll- α declined in the order of alga amount 〉 secchi disc depth（SD） 〉 electrical conductivity （EC）. Additionally, it also demonstrated that the contributions of these three factors were the maximal for the change of chlorophyll-α concentration, total phosphorus（TP） and total nitrogen（TN） were the minimal. All the results showed that BRBPNN model was capable of automated regularization parameter selection and thus it may ensure the excellent generation ability and robustness. Thus, this study laid the foundation for the application of BRBPNN model in the analysis of aquatic ecological data（chlorophyll-α prediction） and the explanation about the effective eutrophication treatment measures for Nanzui water area in Dongting Lake.
基金This work was supported by National Natural Science Foundation(699740 4 1 699740 0 6)
文摘Four layer feedforward regular fuzzy neural networks are constructed. Universal approximations to some continuous fuzzy functions defined on F 0 (R) n by the four layer fuzzy neural networks are shown. At first,multivariate Bernstein polynomials associated with fuzzy valued functions are empolyed to approximate continuous fuzzy valued functions defined on each compact set of R n . Secondly,by introducing cut preserving fuzzy mapping,the equivalent conditions for continuous fuzzy functions that can be arbitrarily closely approximated by regular fuzzy neural networks are shown. Finally a few of sufficient and necessary conditions for characterizing approximation capabilities of regular fuzzy neural networks are obtained. And some concrete fuzzy functions demonstrate our conclusions.
基金Financial support of mechanical engineering center of excellence at Roudbar Azad University
文摘A neural network with a feed forward topology and Bayesian regularization training algorithm is used to predict the austenite formation temperatures （At1 and A13） by considering the percentage of alloying elements in chemical composition of steel. The data base used here involves a large variety of different steel types such as struc- tural steels, stainless steels, rail steels, spring steels, high temperature creep resisting steels and tool steels. Scatter diagrams and mean relative error （MRE） statistical criteria are used to compare the performance of developed neural network with the results of Andrew% empirical equations and a feed forward neural network with ＂gradient descent with momentum＂ training algorithm. The results showed that Bayesian regularization neural network has the best performance. Also, due to the satisfactory results of the developed neural network, it was used to investigate the effect of the chemical composition on Ac1 and At3 temperatures. Results are in accordance with materials science theories.
基金Supported by the National Natural Science Foundation of China(No:69872039)
文摘By defining fuzzy valued simple functions and giving L1(μ) approximations of fuzzy valued integrably bounded functions by such simple functions, the paper analyses by L1(μ)-norm the approximation capability of four-layer feedforward regular fuzzy neural networks to the fuzzy valued integrably bounded function F : Rn → FcO(R). That is, if the transfer functionσ: R→R is non-polynomial and integrable function on each finite interval, F may be innorm approximated by fuzzy valued functions defined as to anydegree of accuracy. Finally some real examples demonstrate the conclusions.
基金Supported by the National Natural Science Foundation of China(71601148)the National Social Science Foundation of China(14ZDA062)Humanities and Social Science Research Foundation of Ministry of Education(14JDGC012)
文摘The regular small-world network, which contains the properties of small-world network and regular network, has recently received substantial attention and has been applied in researches on 2-person games. However, it is a common phenomenon that cooperation always appears as a group behavior. In order to investigate the mechanism of group cooperation, we propose an evolutionary multi-person game model on a regular small-world network based on public goods game theory. Then, to make a comparison of frequency of cooperation among different networks, we carry out simulations on three kinds of networks with the same configuration of average degree： the square lattice, regular small-world network and random regular network. The results of simulation show that the group cooperation will emerge among these three networks when the enhancement factor r exceeds a threshold. Furthermore, time required for full cooperation on regular small-world network is slightly longer than the other networks, which indicates that the compact interactions and random interactions will promote cooperation, while the longer-range links are the obstacles in the emergence of cooperation. In addition, the cooperation would be promoted further by enhancing the random interactions on regular small-world network.
基金Supported by National Natural Science Foundation under Grant No.11002073the Fundamental Research Funds for the Central Universities under Grant No.2011RC0702
文摘We investigate the synchronization ability of four types of regular coupled networks. By introducing the proper error variables and Lyapunov functions, we turn the stability of synchronization manifold into that of null solution of error equations, further, into the negative definiteness of some symmetric matrices, thus we get the sufficient synchronization stability conditions. To test the valid of the results, we take the Chua's circuit as an example. Although the theoretical synchronization thresholds appear to be very conservative, they provide new insights about the influence of topology and scale of networks on synchronization, and that the theoretical results and our numerical simulations are consistent.
基金supported by the National Natural Science Foundation of China(11102094 and 11272024)the Fundamental Research Funds for the Central University(2013RC0904)
文摘Spiking regularity in a clustered Hodgkin–Huxley（HH） neuronal network has been studied in this letter. A stochastic HH neuronal model with channel blocks has been applied as local neuronal model. Effects of the internal channel noise on the spiking regularity are discussed by changing the membrane patch size. We find that when there is no channel blocks in potassium channels, there exist some intermediate membrane patch sizes at which the spiking regularity could reach to a higher level. Spiking regularity increases with the membrane patch size when sodium channels are not blocked. Namely, depending on different channel blocking states, internal channel noise tuned by membrane patch size could have different influence on the spiking regularity of neuronal networks.
基金supported by the National Natural Science Foundation of China(51006052)the NUST Outstanding Scholar Supporting Program
文摘A method for fast 1-fold cross validation is proposed for the regularized extreme learning machine （RELM）. The computational time of fast l-fold cross validation increases as the fold number decreases, which is opposite to that of naive 1-fold cross validation. As opposed to naive l-fold cross validation, fast l-fold cross validation takes the advantage in terms of computational time, especially for the large fold number such as l 〉 20. To corroborate the efficacy and feasibility of fast l-fold cross validation, experiments on five benchmark regression data sets are evaluated.
文摘We consider the problem of minimizing a block separable convex function(possibly nondifferentiable, and including constraints) plus Laplacian regularization, a problem that arises in applications including model fitting, regularizing stratified models, and multi-period portfolio optimization. We develop a distributed majorization-minimization method for this general problem, and derive a complete, self-contained, general,and simple proof of convergence. Our method is able to scale to very large problems, and we illustrate our approach on two applications, demonstrating its scalability and accuracy.
基金supported by National Natural Science Foundation of China(Nos.61425017 and 61773379)the National Key Research&Development Plan of China(No.2017YFB1002804)
文摘As a major component of speech signal processing, speech emotion recognition has become increasingly essential to understanding human communication. Benefitting from deep learning, many researchers have proposed various unsupervised models to extract effective emotional features and supervised models to train emotion recognition systems. In this paper, we utilize semi-supervised ladder networks for speech emotion recognition. The model is trained by minimizing the supervised loss and auxiliary unsupervised cost function. The addition of the unsupervised auxiliary task provides powerful discriminative representations of the input features, and is also regarded as the regularization of the emotional supervised task. We also compare the ladder network with other classical autoencoder structures. The experiments were conducted on the interactive emotional dyadic motion capture (IEMOCAP) database, and the results reveal that the proposed methods achieve superior performance with a small number of labelled data and achieves better performance than other methods.
文摘Topological indices enable to gather information for the underlying topology of chemical structures and networks.Novel harmonic indices have been defined recently.All degree based topological indices are defined by using the classical degree concept.Recently two novel degree concept have been defined in graph theory:ve-degree and evdegree.Ve-degree Zagreb indices have been defined by using ve-degree concept.The prediction power of the ve-degree Zagreb indices is stronger than the classical Zagreb indices.Dominating oxide,silicate and oxygen networks are important network models in view of chemistry,physics and information science.Physical and mathematical properties of dominating oxide,silicate and oxygen networks have been considerably studied in graph theory and network theory.Topological properties of the dominating oxide,silicate and oxygen networks have been intensively investigated for the last few years period.In this study we examined,the first,the fifth harmonic and ev-degree topological indices of dominating oxide(DOX),regular triangulene oxide network(RTOX)and dominating silicate network(DSL).
基金National High-tech Research and Development Program of China (2006AA04Z405)
文摘This article presents two new kinds of artificial neural network （ANN） response surface methods （RSMs）： the ANN RSM based on early stopping technique （ANNRSM-1）, and the ANN RSM based on regularization theory （ANNRSM-2）. The following improvements are made to the conventional ANN RSM （ANNRSM-0）： 1） by monitoring the validation error during the training process, ANNRSM-1 determines the early stopping point and the training stopping point, and the weight vector at the early stopping point, which corresponds to the ANN model with the optimal generalization, is finally returned as the training result; 2） according to the regularization theory, ANNRSM-2 modifies the conventional training performance function by adding to it the sum of squares of the network weights, so the network weights are forced to have smaller values while the training error decreases. Tests show that the performance of ANN RSM becomes much better due to the above-mentioned improvements： first, ANNRSM-1 and ANNRSM-2 approximate to the limit state function （LSF） more accurately than ANNRSM-0; second, the estimated failure probabilities given by ANNRSM-1 and ANNRSM-2 have smaller errors than that obtained by ANNRSM-0; third, compared with ANNRSM-0, ANNRSM-1 and ANNRSM-2 require much fewer data samples to achieve stable failure probability results.
文摘This paper investigates the Morgan＇s problem of Boolean control networks. Based on the matrix expression of logical functions, two key steps are proposed to solve the problem. First, the Boolean control network is converted into an output- decomposed form by constructing a set of consistent outputfriendly subspaces, and a necessary and sufficient condition for the existence of the consistent output-friendly subspaces is obtained. Secondly, a type of state feedback controllers are designed to solve the Morgan＇s problem if it is solvable. By solving a set of matrix equations, a necessary and sufficient condition for converting an output-decomposed form to an input-output decomposed form is given, and by verifying the output controllability matrix, the solvability of Morgan＇s problem is obtained.
文摘We construct a complete-connective regular network based on Self-replication Space and the structural principles of cantor set and Koch curve. A new definition of dimension is proposed in the paper, and we also investigate a simplified method to calculate the dimension of two regular networks. By the study results, we can get a extension: the formation of Euclidean space may be built by the process of the Big Bang's continuously growing at a constant rate of three times.
文摘This article is intended as a proposal for a numerical model for the prediction of the ultimate moment of a reinforced concrete beam reinforced with composite materials based on neural networks, which are classified in the artificial intelligence method. In this work, a RBF network or radial basis function type model was created and tested. The validation of the RBF architecture consists in judging its predictive capacity by using the weights and biases computed during the training, to apply them to another database which did not participate to the training and testing of the model. So, with Bayesian regularization, a maximum error of 0.0813 Tm in absolute value was found between the targets and predicted outputs. The value of the mean square error MSE = 1.1106 * 10<sup>-4</sup> allowed us to quantify and justify the prediction performance of this network. Through this article, RBF network model was justified perform and can be used and exploited by our engineers with a high reliability rate.
文摘The aim of this paper is to broaden the application of Stochastic Configuration Network (SCN) in the semi-supervised domain by utilizing common unlabeled data in daily life. It can enhance the classification accuracy of decentralized SCN algorithms while effectively protecting user privacy. To this end, we propose a decentralized semi-supervised learning algorithm for SCN, called DMT-SCN, which introduces teacher and student models by combining the idea of consistency regularization to improve the response speed of model iterations. In order to reduce the possible negative impact of unsupervised data on the model, we purposely change the way of adding noise to the unlabeled data. Simulation results show that the algorithm can effectively utilize unlabeled data to improve the classification accuracy of SCN training and is robust under different ground simulation environments.
