In this paper, polynomial fuzzy neural network classifiers (PFNNCs) is proposed by means of density fuzzy c-means and L2-norm regularization. The overall design of PFNNCs was realized by means of fuzzy rules that come...In this paper, polynomial fuzzy neural network classifiers (PFNNCs) is proposed by means of density fuzzy c-means and L2-norm regularization. The overall design of PFNNCs was realized by means of fuzzy rules that come in form of three parts, namely premise part, consequence part and aggregation part. The premise part was developed by density fuzzy c-means that helps determine the apex parameters of membership functions, while the consequence part was realized by means of two types of polynomials including linear and quadratic. L2-norm regularization that can alleviate the overfitting problem was exploited to estimate the parameters of polynomials, which constructed the aggregation part. Experimental results of several data sets demonstrate that the proposed classifiers show higher classification accuracy in comparison with some other classifiers reported in the literature.展开更多
Bayesian empirical likelihood is a semiparametric method that combines parametric priors and nonparametric likelihoods, that is, replacing the parametric likelihood function in Bayes theorem with a nonparametric empir...Bayesian empirical likelihood is a semiparametric method that combines parametric priors and nonparametric likelihoods, that is, replacing the parametric likelihood function in Bayes theorem with a nonparametric empirical likelihood function, which can be used without assuming the distribution of the data. It can effectively avoid the problems caused by the wrong setting of the model. In the variable selection based on Bayesian empirical likelihood, the penalty term is introduced into the model in the form of parameter prior. In this paper, we propose a novel variable selection method, L<sub>1/2</sub> regularization based on Bayesian empirical likelihood. The L<sub>1/2</sub> penalty is introduced into the model through a scale mixture of uniform representation of generalized Gaussian prior, and the posterior distribution is then sampled using MCMC method. Simulations demonstrate that the proposed method can have better predictive ability when the error violates the zero-mean normality assumption of the standard parameter model, and can perform variable selection.展开更多
High-dimensional and sparse(HiDS)matrices commonly arise in various industrial applications,e.g.,recommender systems(RSs),social networks,and wireless sensor networks.Since they contain rich information,how to accurat...High-dimensional and sparse(HiDS)matrices commonly arise in various industrial applications,e.g.,recommender systems(RSs),social networks,and wireless sensor networks.Since they contain rich information,how to accurately represent them is of great significance.A latent factor(LF)model is one of the most popular and successful ways to address this issue.Current LF models mostly adopt L2-norm-oriented Loss to represent an HiDS matrix,i.e.,they sum the errors between observed data and predicted ones with L2-norm.Yet L2-norm is sensitive to outlier data.Unfortunately,outlier data usually exist in such matrices.For example,an HiDS matrix from RSs commonly contains many outlier ratings due to some heedless/malicious users.To address this issue,this work proposes a smooth L1-norm-oriented latent factor(SL-LF)model.Its main idea is to adopt smooth L1-norm rather than L2-norm to form its Loss,making it have both strong robustness and high accuracy in predicting the missing data of an HiDS matrix.Experimental results on eight HiDS matrices generated by industrial applications verify that the proposed SL-LF model not only is robust to the outlier data but also has significantly higher prediction accuracy than state-of-the-art models when they are used to predict the missing data of HiDS matrices.展开更多
Color image super-resolution reconstruction based on the sparse representation model usually adopts the regularization norm(e.g.,L1 or L2).These methods have limited ability to keep image texture detail to some extent...Color image super-resolution reconstruction based on the sparse representation model usually adopts the regularization norm(e.g.,L1 or L2).These methods have limited ability to keep image texture detail to some extent and are easy to cause the problem of blurring details and color artifacts in color reconstructed images.This paper presents a color super-resolution reconstruction method combining the L2/3 sparse regularization model with color channel constraints.The method converts the low-resolution color image from RGB to YCbCr.The L2/3 sparse regularization model is designed to reconstruct the brightness channel of the input low-resolution color image.Then the color channel-constraint method is adopted to remove artifacts of the reconstructed highresolution image.The method not only ensures the reconstruction quality of the color image details,but also improves the removal ability of color artifacts.The experimental results on natural images validate that our method has improved both subjective and objective evaluation.展开更多
Even though much advancements have been achieved with regards to the recognition of handwritten characters,researchers still face difficulties with the handwritten character recognition problem,especially with the adv...Even though much advancements have been achieved with regards to the recognition of handwritten characters,researchers still face difficulties with the handwritten character recognition problem,especially with the advent of new datasets like the Extended Modified National Institute of Standards and Technology dataset(EMNIST).The EMNIST dataset represents a challenge for both machine-learning and deep-learning techniques due to inter-class similarity and intra-class variability.Inter-class similarity exists because of the similarity between the shapes of certain characters in the dataset.The presence of intra-class variability is mainly due to different shapes written by different writers for the same character.In this research,we have optimized a deep residual network to achieve higher accuracy vs.the published state-of-the-art results.This approach is mainly based on the prebuilt deep residual network model ResNet18,whose architecture has been enhanced by using the optimal number of residual blocks and the optimal size of the receptive field of the first convolutional filter,the replacement of the first max-pooling filter by an average pooling filter,and the addition of a drop-out layer before the fully connected layer.A distinctive modification has been introduced by replacing the final addition layer with a depth concatenation layer,which resulted in a novel deep architecture having higher accuracy vs.the pure residual architecture.Moreover,the dataset images’sizes have been adjusted to optimize their visibility in the network.Finally,by tuning the training hyperparameters and using rotation and shear augmentations,the proposed model outperformed the state-of-the-art models by achieving average accuracies of 95.91%and 90.90%for the Letters and Balanced dataset sections,respectively.Furthermore,the average accuracies were improved to 95.9%and 91.06%for the Letters and Balanced sections,respectively,by using a group of 5 instances of the trained models and averaging the output class probabilities.展开更多
The generative adversarial network(GAN)is first proposed in 2014,and this kind of network model is machine learning systems that can learn to measure a given distribution of data,one of the most important applications...The generative adversarial network(GAN)is first proposed in 2014,and this kind of network model is machine learning systems that can learn to measure a given distribution of data,one of the most important applications is style transfer.Style transfer is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image.CYCLE-GAN is a classic GAN model,which has a wide range of scenarios in style transfer.Considering its unsupervised learning characteristics,the mapping is easy to be learned between an input image and an output image.However,it is difficult for CYCLE-GAN to converge and generate high-quality images.In order to solve this problem,spectral normalization is introduced into each convolutional kernel of the discriminator.Every convolutional kernel reaches Lipschitz stability constraint with adding spectral normalization and the value of the convolutional kernel is limited to[0,1],which promotes the training process of the proposed model.Besides,we use pretrained model(VGG16)to control the loss of image content in the position of l1 regularization.To avoid overfitting,l1 regularization term and l2 regularization term are both used in the object loss function.In terms of Frechet Inception Distance(FID)score evaluation,our proposed model achieves outstanding performance and preserves more discriminative features.Experimental results show that the proposed model converges faster and achieves better FID scores than the state of the art.展开更多
We derive a sharp nonasymptotic bound of parameter estimation of the L1/2 regularization. The bound shows that the solutions of the L1/2 regularization can achieve a loss within logarithmic factor of an ideal mean squ...We derive a sharp nonasymptotic bound of parameter estimation of the L1/2 regularization. The bound shows that the solutions of the L1/2 regularization can achieve a loss within logarithmic factor of an ideal mean squared error and therefore underlies the feasibility and effectiveness of the L1/2 regularization. Interestingly, when applied to compressive sensing, the L1/2 regularization scheme has exhibited a very promising capability of completed recovery from a much less sampling information. As compared with the Lp (0 〈 p 〈 1) penalty, it is appeared that the L1/2 penalty can always yield the most sparse solution among all the Lv penalty when 1/2 〈 p 〈 1, and when 0 〈 p 〈 1/2, the Lp penalty exhibits the similar properties as the L1/2 penalty. This suggests that the L1/2 regularization scheme can be accepted as the best and therefore the representative of all the Lp (0 〈 p 〈 1) regularization schemes.展开更多
Presents the abstract L...-norm error estimate of nonconforming finite element method. Use of the Aubin Nitsche Lemma in estimating nonconforming finite element methods; Details on the equations.
Increasing the robustness to the unknown uncertainty and simultaneously enhancing the sensibility to the faults is one of the important issues considered in the fault detection development. Considering the L2-gain of ...Increasing the robustness to the unknown uncertainty and simultaneously enhancing the sensibility to the faults is one of the important issues considered in the fault detection development. Considering the L2-gain of residual system, this paper deals the observer-based fault detection problem. By using of H∞ control theory,an LMI approach to design fault detection observer is given. A numerical example is used to illustrate the effectiveness of the proposed approach.展开更多
From fraud detection to speech recognition,including price prediction,Machine Learning(ML)applications are manifold and can significantly improve different areas.Nevertheless,machine learning models are vulnerable and...From fraud detection to speech recognition,including price prediction,Machine Learning(ML)applications are manifold and can significantly improve different areas.Nevertheless,machine learning models are vulnerable and are exposed to different security and privacy attacks.Hence,these issues should be addressed while using ML models to preserve the security and privacy of the data used.There is a need to secure ML models,especially in the training phase to preserve the privacy of the training datasets and to minimise the information leakage.In this paper,we present an overview of ML threats and vulnerabilities,and we highlight current progress in the research works proposing defence techniques againstML security and privacy attacks.The relevant background for the different attacks occurring in both the training and testing/inferring phases is introduced before presenting a detailed overview of Membership Inference Attacks(MIA)and the related countermeasures.In this paper,we introduce a countermeasure against membership inference attacks(MIA)on Conventional Neural Networks(CNN)based on dropout and L2 regularization.Through experimental analysis,we demonstrate that this defence technique can mitigate the risks of MIA attacks while ensuring an acceptable accuracy of the model.Indeed,using CNN model training on two datasets CIFAR-10 and CIFAR-100,we empirically verify the ability of our defence strategy to decrease the impact of MIA on our model and we compare results of five different classifiers.Moreover,we present a solution to achieve a trade-off between the performance of themodel and the mitigation of MIA attack.展开更多
The physical model is described by a seepage coupled system for simulating numerically three-dimensional chemical oil recovery, whose mathematical description includes three equations to interpret main concepts. The p...The physical model is described by a seepage coupled system for simulating numerically three-dimensional chemical oil recovery, whose mathematical description includes three equations to interpret main concepts. The pressure equation is a nonlinear parabolic equation, the concentration is defined by a convection-diffusion equation and the saturations of different components are stated by nonlinear convection-diffusion equations. The transport pressure appears in the concentration equation and saturation equations in the form of Darcy velocity, and controls their processes. The flow equation is solved by the conservative mixed volume element and the accuracy is improved one order for approximating Darcy velocity. The method of characteristic mixed volume element is applied to solve the concentration, where the diffusion is discretized by a mixed volume element method and the convection is treated by the method of characteristics. The characteristics can confirm strong computational stability at sharp fronts and it can avoid numerical dispersion and nonphysical oscillation. The scheme can adopt a large step while its numerical results have small time-truncation error and high order of accuracy. The mixed volume element method has the law of conservation on every element for the diffusion and it can obtain numerical solutions of the concentration and adjoint vectors. It is most important in numerical simulation to ensure the physical conservative nature. The saturation different components are obtained by the method of characteristic fractional step difference. The computational work is shortened greatly by decomposing a three-dimensional problem into three successive one-dimensional problems and it is completed easily by using the algorithm of speedup. Using the theory and technique of a priori estimates of differential equations, we derive an optimal second order estimates in 12 norm. Numerical examples are given to show the effectiveness and practicability and the method is testified as a powerful tool to solve the important problems.展开更多
Compared with traditional learning methods such as the back propagation(BP)method,extreme learning machine provides much faster learning speed and needs less human intervention,and thus has been widely used.In this pa...Compared with traditional learning methods such as the back propagation(BP)method,extreme learning machine provides much faster learning speed and needs less human intervention,and thus has been widely used.In this paper we combine the L1/2regularization method with extreme learning machine to prune extreme learning machine.A variable learning coefcient is employed to prevent too large a learning increment.A numerical experiment demonstrates that a network pruned by L1/2regularization has fewer hidden nodes but provides better performance than both the original network and the network pruned by L2regularization.展开更多
基金This work was supported in part by the National Natural Science Foundation of China under Grant 61673295the Natural Science Foundation of Tianjin under Grant 18JCYBJC85200by the National College Students’ innovation and entrepreneurship project under Grant 201710060041.
文摘In this paper, polynomial fuzzy neural network classifiers (PFNNCs) is proposed by means of density fuzzy c-means and L2-norm regularization. The overall design of PFNNCs was realized by means of fuzzy rules that come in form of three parts, namely premise part, consequence part and aggregation part. The premise part was developed by density fuzzy c-means that helps determine the apex parameters of membership functions, while the consequence part was realized by means of two types of polynomials including linear and quadratic. L2-norm regularization that can alleviate the overfitting problem was exploited to estimate the parameters of polynomials, which constructed the aggregation part. Experimental results of several data sets demonstrate that the proposed classifiers show higher classification accuracy in comparison with some other classifiers reported in the literature.
文摘Bayesian empirical likelihood is a semiparametric method that combines parametric priors and nonparametric likelihoods, that is, replacing the parametric likelihood function in Bayes theorem with a nonparametric empirical likelihood function, which can be used without assuming the distribution of the data. It can effectively avoid the problems caused by the wrong setting of the model. In the variable selection based on Bayesian empirical likelihood, the penalty term is introduced into the model in the form of parameter prior. In this paper, we propose a novel variable selection method, L<sub>1/2</sub> regularization based on Bayesian empirical likelihood. The L<sub>1/2</sub> penalty is introduced into the model through a scale mixture of uniform representation of generalized Gaussian prior, and the posterior distribution is then sampled using MCMC method. Simulations demonstrate that the proposed method can have better predictive ability when the error violates the zero-mean normality assumption of the standard parameter model, and can perform variable selection.
基金supported in part by the National Natural Science Foundation of China(61702475,61772493,61902370,62002337)in part by the Natural Science Foundation of Chongqing,China(cstc2019jcyj-msxmX0578,cstc2019jcyjjqX0013)+1 种基金in part by the Chinese Academy of Sciences“Light of West China”Program,in part by the Pioneer Hundred Talents Program of Chinese Academy of Sciencesby Technology Innovation and Application Development Project of Chongqing,China(cstc2019jscx-fxydX0027)。
文摘High-dimensional and sparse(HiDS)matrices commonly arise in various industrial applications,e.g.,recommender systems(RSs),social networks,and wireless sensor networks.Since they contain rich information,how to accurately represent them is of great significance.A latent factor(LF)model is one of the most popular and successful ways to address this issue.Current LF models mostly adopt L2-norm-oriented Loss to represent an HiDS matrix,i.e.,they sum the errors between observed data and predicted ones with L2-norm.Yet L2-norm is sensitive to outlier data.Unfortunately,outlier data usually exist in such matrices.For example,an HiDS matrix from RSs commonly contains many outlier ratings due to some heedless/malicious users.To address this issue,this work proposes a smooth L1-norm-oriented latent factor(SL-LF)model.Its main idea is to adopt smooth L1-norm rather than L2-norm to form its Loss,making it have both strong robustness and high accuracy in predicting the missing data of an HiDS matrix.Experimental results on eight HiDS matrices generated by industrial applications verify that the proposed SL-LF model not only is robust to the outlier data but also has significantly higher prediction accuracy than state-of-the-art models when they are used to predict the missing data of HiDS matrices.
基金supported by the National Natural Science Foundation of China(61761028)。
文摘Color image super-resolution reconstruction based on the sparse representation model usually adopts the regularization norm(e.g.,L1 or L2).These methods have limited ability to keep image texture detail to some extent and are easy to cause the problem of blurring details and color artifacts in color reconstructed images.This paper presents a color super-resolution reconstruction method combining the L2/3 sparse regularization model with color channel constraints.The method converts the low-resolution color image from RGB to YCbCr.The L2/3 sparse regularization model is designed to reconstruct the brightness channel of the input low-resolution color image.Then the color channel-constraint method is adopted to remove artifacts of the reconstructed highresolution image.The method not only ensures the reconstruction quality of the color image details,but also improves the removal ability of color artifacts.The experimental results on natural images validate that our method has improved both subjective and objective evaluation.
文摘Even though much advancements have been achieved with regards to the recognition of handwritten characters,researchers still face difficulties with the handwritten character recognition problem,especially with the advent of new datasets like the Extended Modified National Institute of Standards and Technology dataset(EMNIST).The EMNIST dataset represents a challenge for both machine-learning and deep-learning techniques due to inter-class similarity and intra-class variability.Inter-class similarity exists because of the similarity between the shapes of certain characters in the dataset.The presence of intra-class variability is mainly due to different shapes written by different writers for the same character.In this research,we have optimized a deep residual network to achieve higher accuracy vs.the published state-of-the-art results.This approach is mainly based on the prebuilt deep residual network model ResNet18,whose architecture has been enhanced by using the optimal number of residual blocks and the optimal size of the receptive field of the first convolutional filter,the replacement of the first max-pooling filter by an average pooling filter,and the addition of a drop-out layer before the fully connected layer.A distinctive modification has been introduced by replacing the final addition layer with a depth concatenation layer,which resulted in a novel deep architecture having higher accuracy vs.the pure residual architecture.Moreover,the dataset images’sizes have been adjusted to optimize their visibility in the network.Finally,by tuning the training hyperparameters and using rotation and shear augmentations,the proposed model outperformed the state-of-the-art models by achieving average accuracies of 95.91%and 90.90%for the Letters and Balanced dataset sections,respectively.Furthermore,the average accuracies were improved to 95.9%and 91.06%for the Letters and Balanced sections,respectively,by using a group of 5 instances of the trained models and averaging the output class probabilities.
基金This work is supported by the National Natural Science Foundation of China(No.61702226)the 111 Project(B12018)+1 种基金the Natural Science Foundation of Jiangsu Province(No.BK20170200)the Fundamental Research Funds for the Central Universities(No.JUSRP11854).
文摘The generative adversarial network(GAN)is first proposed in 2014,and this kind of network model is machine learning systems that can learn to measure a given distribution of data,one of the most important applications is style transfer.Style transfer is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image.CYCLE-GAN is a classic GAN model,which has a wide range of scenarios in style transfer.Considering its unsupervised learning characteristics,the mapping is easy to be learned between an input image and an output image.However,it is difficult for CYCLE-GAN to converge and generate high-quality images.In order to solve this problem,spectral normalization is introduced into each convolutional kernel of the discriminator.Every convolutional kernel reaches Lipschitz stability constraint with adding spectral normalization and the value of the convolutional kernel is limited to[0,1],which promotes the training process of the proposed model.Besides,we use pretrained model(VGG16)to control the loss of image content in the position of l1 regularization.To avoid overfitting,l1 regularization term and l2 regularization term are both used in the object loss function.In terms of Frechet Inception Distance(FID)score evaluation,our proposed model achieves outstanding performance and preserves more discriminative features.Experimental results show that the proposed model converges faster and achieves better FID scores than the state of the art.
基金supported by National Natural Science Foundation of China(Grant Nos.11171212 and60975036)supported by National Natural Science Foundation of China(Grant No.6175054)
文摘We derive a sharp nonasymptotic bound of parameter estimation of the L1/2 regularization. The bound shows that the solutions of the L1/2 regularization can achieve a loss within logarithmic factor of an ideal mean squared error and therefore underlies the feasibility and effectiveness of the L1/2 regularization. Interestingly, when applied to compressive sensing, the L1/2 regularization scheme has exhibited a very promising capability of completed recovery from a much less sampling information. As compared with the Lp (0 〈 p 〈 1) penalty, it is appeared that the L1/2 penalty can always yield the most sparse solution among all the Lv penalty when 1/2 〈 p 〈 1, and when 0 〈 p 〈 1/2, the Lp penalty exhibits the similar properties as the L1/2 penalty. This suggests that the L1/2 regularization scheme can be accepted as the best and therefore the representative of all the Lp (0 〈 p 〈 1) regularization schemes.
文摘Presents the abstract L...-norm error estimate of nonconforming finite element method. Use of the Aubin Nitsche Lemma in estimating nonconforming finite element methods; Details on the equations.
基金Supported by Shanghai postdoctoral found(2000478)
文摘Increasing the robustness to the unknown uncertainty and simultaneously enhancing the sensibility to the faults is one of the important issues considered in the fault detection development. Considering the L2-gain of residual system, this paper deals the observer-based fault detection problem. By using of H∞ control theory,an LMI approach to design fault detection observer is given. A numerical example is used to illustrate the effectiveness of the proposed approach.
文摘From fraud detection to speech recognition,including price prediction,Machine Learning(ML)applications are manifold and can significantly improve different areas.Nevertheless,machine learning models are vulnerable and are exposed to different security and privacy attacks.Hence,these issues should be addressed while using ML models to preserve the security and privacy of the data used.There is a need to secure ML models,especially in the training phase to preserve the privacy of the training datasets and to minimise the information leakage.In this paper,we present an overview of ML threats and vulnerabilities,and we highlight current progress in the research works proposing defence techniques againstML security and privacy attacks.The relevant background for the different attacks occurring in both the training and testing/inferring phases is introduced before presenting a detailed overview of Membership Inference Attacks(MIA)and the related countermeasures.In this paper,we introduce a countermeasure against membership inference attacks(MIA)on Conventional Neural Networks(CNN)based on dropout and L2 regularization.Through experimental analysis,we demonstrate that this defence technique can mitigate the risks of MIA attacks while ensuring an acceptable accuracy of the model.Indeed,using CNN model training on two datasets CIFAR-10 and CIFAR-100,we empirically verify the ability of our defence strategy to decrease the impact of MIA on our model and we compare results of five different classifiers.Moreover,we present a solution to achieve a trade-off between the performance of themodel and the mitigation of MIA attack.
基金Supported by the National Natural Science Foundation of China(11101124 and 11271231)Natural Science Foundation of Shandong Province(ZR2016AM08)National Tackling Key Problems Program(2011ZX05052,2011ZX05011-004)
文摘The physical model is described by a seepage coupled system for simulating numerically three-dimensional chemical oil recovery, whose mathematical description includes three equations to interpret main concepts. The pressure equation is a nonlinear parabolic equation, the concentration is defined by a convection-diffusion equation and the saturations of different components are stated by nonlinear convection-diffusion equations. The transport pressure appears in the concentration equation and saturation equations in the form of Darcy velocity, and controls their processes. The flow equation is solved by the conservative mixed volume element and the accuracy is improved one order for approximating Darcy velocity. The method of characteristic mixed volume element is applied to solve the concentration, where the diffusion is discretized by a mixed volume element method and the convection is treated by the method of characteristics. The characteristics can confirm strong computational stability at sharp fronts and it can avoid numerical dispersion and nonphysical oscillation. The scheme can adopt a large step while its numerical results have small time-truncation error and high order of accuracy. The mixed volume element method has the law of conservation on every element for the diffusion and it can obtain numerical solutions of the concentration and adjoint vectors. It is most important in numerical simulation to ensure the physical conservative nature. The saturation different components are obtained by the method of characteristic fractional step difference. The computational work is shortened greatly by decomposing a three-dimensional problem into three successive one-dimensional problems and it is completed easily by using the algorithm of speedup. Using the theory and technique of a priori estimates of differential equations, we derive an optimal second order estimates in 12 norm. Numerical examples are given to show the effectiveness and practicability and the method is testified as a powerful tool to solve the important problems.
基金Project supported by the National Natural Science Foundation of China(No.11171367)the Fundamental Research Funds for the Central Universities,China
文摘Compared with traditional learning methods such as the back propagation(BP)method,extreme learning machine provides much faster learning speed and needs less human intervention,and thus has been widely used.In this paper we combine the L1/2regularization method with extreme learning machine to prune extreme learning machine.A variable learning coefcient is employed to prevent too large a learning increment.A numerical experiment demonstrates that a network pruned by L1/2regularization has fewer hidden nodes but provides better performance than both the original network and the network pruned by L2regularization.