Vector neural network(VNN)is one of the most important methods to process interval data.However,the VNN,which contains a great number of multiply-accumulate(MAC)operations,often adopts pure numerical calculation metho...Vector neural network(VNN)is one of the most important methods to process interval data.However,the VNN,which contains a great number of multiply-accumulate(MAC)operations,often adopts pure numerical calculation method,and thus is difficult to be miniaturized for the embedded applications.In this paper,we propose a memristor based vector-type backpropagation(MVTBP)architecture which utilizes memristive arrays to accelerate the MAC operations of interval data.Owing to the unique brain-like synaptic characteristics of memristive devices,e.g.,small size,low power consumption,and high integration density,the proposed architecture can be implemented with low area and power consumption cost and easily applied to embedded systems.The simulation results indicate that the proposed architecture has better identification performance and noise tolerance.When the device precision is 6 bits and the error deviation level(EDL)is 20%,the proposed architecture can achieve an identification rate,which is about 92%higher than that for interval-value testing sample and 81%higher than that for scalar-value testing sample.展开更多
Option pricing has become one of the quite important parts of the financial market. As the market is always dynamic, it is really difficult to predict the option price accurately. For this reason, various machine lear...Option pricing has become one of the quite important parts of the financial market. As the market is always dynamic, it is really difficult to predict the option price accurately. For this reason, various machine learning techniques have been designed and developed to deal with the problem of predicting the future trend of option price. In this paper, we compare the effectiveness of Support Vector Machine (SVM) and Artificial Neural Network (ANN) models for the prediction of option price. Both models are tested with a benchmark publicly available dataset namely SPY option price-2015 in both testing and training phases. The converted data through Principal Component Analysis (PCA) is used in both models to achieve better prediction accuracy. On the other hand, the entire dataset is partitioned into two groups of training (70%) and test sets (30%) to avoid overfitting problem. The outcomes of the SVM model are compared with those of the ANN model based on the root mean square errors (RMSE). It is demonstrated by the experimental results that the ANN model performs better than the SVM model, and the predicted option prices are in good agreement with the corresponding actual option prices.展开更多
Accurate cost estimation at the early stage of a construction project is key factor in a project’s success. But it is difficult to quickly and accurately estimate construction costs at the planning stage, when drawin...Accurate cost estimation at the early stage of a construction project is key factor in a project’s success. But it is difficult to quickly and accurately estimate construction costs at the planning stage, when drawings, documentation and the like are still incomplete. As such, various techniques have been applied to accurately estimate construction costs at an early stage, when project information is limited. While the various techniques have their pros and cons, there has been little effort made to determine the best technique in terms of cost estimating performance. The objective of this research is to compare the accuracy of three estimating techniques (regression analysis (RA), neural network (NN), and support vector machine techniques (SVM)) by performing estimations of construction costs. By comparing the accuracy of these techniques using historical cost data, it was found that NN model showed more accurate estimation results than the RA and SVM models. Consequently, it is determined that NN model is most suitable for estimating the cost of school building projects.展开更多
In this article, we consider the global chaotic synchronization of general cou- pled neural networks, in which subsystems have both discrete and distributed delays. Stochastic perturbations between subsystems are also...In this article, we consider the global chaotic synchronization of general cou- pled neural networks, in which subsystems have both discrete and distributed delays. Stochastic perturbations between subsystems are also considered. On the basis of two sim- ple adaptive pinning feedback control schemes, Lyapunov functional method, and stochas- tic analysis approach, several sufficient conditions are developed to guarantee global syn- chronization of the coupled neural networks with two kinds of delay couplings, even if only partial states of the nodes are coupled. The outer-coupling matrices may be symmetric or asymmetric. Unlike existing results that an isolate node is introduced as the pinning target, we pin to help the network realizing synchronization without introducing any iso- late node when the network is not synchronized. As a by product, sufficient conditions under which the network realizes synchronization without control are derived. Numerical simulations confirm the effectiveness of the obtained results.展开更多
A new intrusion detection method based on learning vector quantization （LVQ） with low overhead and high efficiency is presented. The computer vision system employs LVQ neural networks as classifier to recognize intr...A new intrusion detection method based on learning vector quantization （LVQ） with low overhead and high efficiency is presented. The computer vision system employs LVQ neural networks as classifier to recognize intrusion. The recognition process includes three stages： （1） feature selection and data normalization processing;（2） learning the training data selected from the feature data set; （3） identifying the intrusion and generating the result report of machine condition classification. Experimental results show that the proposed method is promising in terms of detection accuracy, computational expense and implementation for intrusion detection.展开更多
In this paper, sixty-eight research articles published between 2000 and 2017 as well as textbooks which employed four classification algorithms: K-Nearest-Neighbor (KNN), Support Vector Machines (SVM), Random Forest (...In this paper, sixty-eight research articles published between 2000 and 2017 as well as textbooks which employed four classification algorithms: K-Nearest-Neighbor (KNN), Support Vector Machines (SVM), Random Forest (RF) and Neural Network (NN) as the main statistical tools were reviewed. The aim was to examine and compare these nonparametric classification methods on the following attributes: robustness to training data, sensitivity to changes, data fitting, stability, ability to handle large data sizes, sensitivity to noise, time invested in parameter tuning, and accuracy. The performances, strengths and shortcomings of each of the algorithms were examined, and finally, a conclusion was arrived at on which one has higher performance. It was evident from the literature reviewed that RF is too sensitive to small changes in the training dataset and is occasionally unstable and tends to overfit in the model. KNN is easy to implement and understand but has a major drawback of becoming significantly slow as the size of the data in use grows, while the ideal value of K for the KNN classifier is difficult to set. SVM and RF are insensitive to noise or overtraining, which shows their ability in dealing with unbalanced data. Larger input datasets will lengthen classification times for NN and KNN more than for SVM and RF. Among these nonparametric classification methods, NN has the potential to become a more widely used classification algorithm, but because of their time-consuming parameter tuning procedure, high level of complexity in computational processing, the numerous types of NN architectures to choose from and the high number of algorithms used for training, most researchers recommend SVM and RF as easier and wieldy used methods which repeatedly achieve results with high accuracies and are often faster to implement.展开更多
Artificial neural network models are a popular estimation tool for fitting nonlinear relationships because they require no assumptions about the form of the fitting function,non-Gaussian distributions,multicollinearit...Artificial neural network models are a popular estimation tool for fitting nonlinear relationships because they require no assumptions about the form of the fitting function,non-Gaussian distributions,multicollinearity,outliers and noise in the data.The problems of backpropagation models using artificial neural networks include determination of the structure of the network and overlearning courses.According to data from 1981 to 2008 from 15 permanent sample plots on Dagangshan Mountain in Jiangxi Province,a back-propagation artificial neural network model(BPANN)and a support vector machine model(SVM)for basal area of Chinese fir(Cunninghamia lanceolata)plantations were constructed using four kinds of prediction factors,including stand age,site index,surviving stem numbers and quadratic mean diameters.Artificial intelligence methods,especially SVM,could be effective in describing stand basal area growth of Chinese fir under different growth conditions with higher simulation precision than traditional regression models.SVM and the Chapman–Richards nonlinear mixed-effects model had less systematic bias than the BPANN.展开更多
Human body posture recognition has attracted considerable attention in recent years in wireless body area networks(WBAN). In order to precisely recognize human body posture,many recognition algorithms have been propos...Human body posture recognition has attracted considerable attention in recent years in wireless body area networks(WBAN). In order to precisely recognize human body posture,many recognition algorithms have been proposed.However, the recognition rate is relatively low. In this paper, we apply back propagation(BP) neural network as a classifier to recognizing human body posture, where signals are collected from VG350 acceleration sensor and a posture signal collection system based on WBAN is designed. Human body signal vector magnitude(SVM) and tri-axial acceleration sensor data are used to describe the human body postures. We are able to recognize 4postures: Walk, Run, Squat and Sit. Our posture recognition rate is up to 91.67%. Furthermore, we find an implied relationship between hidden layer neurons and the posture recognition rate. The proposed human body posture recognition algorithm lays the foundation for the subsequent applications.展开更多
To make recommendation on items from the user for historical user rating several intelligent systems are using. The most common method is Recommendation systems. The main areas which play major roles are social networ...To make recommendation on items from the user for historical user rating several intelligent systems are using. The most common method is Recommendation systems. The main areas which play major roles are social networking, digital marketing, online shopping and E-commerce. Recommender system consists of several techniques for recommendations. Here we used the well known approach named as Collaborative filtering (CF). There are two types of problems mainly available with collaborative filtering. They are complete cold start (CCS) problem and incomplete cold start (ICS) problem. The authors proposed three novel methods such as collaborative filtering, and artificial neural networks and at last support vector machine to resolve CCS as well ICS problems. Based on the specific deep neural network SADE we can be able to remove the characteristics of products. By using sequential active of users and product characteristics we have the capability to adapt the cold start product ratings with the applications of the state of the art CF model, time SVD++. The proposed system consists of Netflix rating dataset which is used to perform the baseline techniques for rating prediction of cold start items. The calculation of two proposed recommendation techniques is compared on ICS items, and it is proved that it will be adaptable method. The proposed method can be able to transfer the products since cold start transfers to non-cold start status. Artificial Neural Network (ANN) is employed here to extract the item content features. One of the user preferences such as temporal dynamics is used to obtain the contented characteristics into predictions to overcome those problems. For the process of classification we have used linear support vector machine classifiers to receive the better performance when compared with the earlier methods.展开更多
Protein Secondary Structure Prediction (PSSP) is considered as one of the major challenging tasks in bioinformatics, so many solutions have been proposed to solve that problem via trying to achieve more accurate predi...Protein Secondary Structure Prediction (PSSP) is considered as one of the major challenging tasks in bioinformatics, so many solutions have been proposed to solve that problem via trying to achieve more accurate prediction results. The goal of this paper is to develop and implement an intelligent based system to predict secondary structure of a protein from its primary amino acid sequence by using five models of Neural Network (NN). These models are Feed Forward Neural Network (FNN), Learning Vector Quantization (LVQ), Probabilistic Neural Network (PNN), Convolutional Neural Network (CNN), and CNN Fine Tuning for PSSP. To evaluate our approaches two datasets have been used. The first one contains 114 protein samples, and the second one contains 1845 protein samples.展开更多
In order to solve the problems of small sample over-fitting and local minima when neural networks learn online, a novel method of predicting network bandwidth based on support vector machines(SVM) is proposed. The pre...In order to solve the problems of small sample over-fitting and local minima when neural networks learn online, a novel method of predicting network bandwidth based on support vector machines(SVM) is proposed. The prediction and learning online will be completed by the proposed moving window learning algorithm(MWLA). The simulation research is done to validate the proposed method, which is compared with the method based on neural networks.展开更多
External factors, such as social media and financial news, can have wide-spread effects on stock price movement. For this reason, social media is considered a useful resource for precise market predictions. In this pa...External factors, such as social media and financial news, can have wide-spread effects on stock price movement. For this reason, social media is considered a useful resource for precise market predictions. In this paper, we show the effectiveness of using Twitter posts to predict stock prices. We start by training various models on the Sentiment 140 Twitter data. We found that Support Vector Machines (SVM) performed best (0.83 accuracy) in the sentimental analysis, so we used it to predict the average sentiment of tweets for each day that the market was open. Next, we use the sentimental analysis of one year’s data of tweets that contain the “stock market”, “stocktwits”, “AAPL” keywords, with the goal of predicting the corresponding stock prices of Apple Inc. (AAPL) and the US’s Dow Jones Industrial Average (DJIA) index prices. Two models, Boosted Regression Trees and Multilayer Perceptron Neural Networks were used to predict the closing price difference of AAPL and DJIA prices. We show that neural networks perform substantially better than traditional models for stocks’ price prediction.展开更多
In the contemporary era, the proliferation of information technology has led to an unprecedented surge in data generation, with this data being dispersed across a multitude of mobile devices. Facing these situations a...In the contemporary era, the proliferation of information technology has led to an unprecedented surge in data generation, with this data being dispersed across a multitude of mobile devices. Facing these situations and the training of deep learning model that needs great computing power support, the distributed algorithm that can carry out multi-party joint modeling has attracted everyone’s attention. The distributed training mode relieves the huge pressure of centralized model on computer computing power and communication. However, most distributed algorithms currently work in a master-slave mode, often including a central server for coordination, which to some extent will cause communication pressure, data leakage, privacy violations and other issues. To solve these problems, a decentralized fully distributed algorithm based on deep random weight neural network is proposed. The algorithm decomposes the original objective function into several sub-problems under consistency constraints, combines the decentralized average consensus (DAC) and alternating direction method of multipliers (ADMM), and achieves the goal of joint modeling and training through local calculation and communication of each node. Finally, we compare the proposed decentralized algorithm with several centralized deep neural networks with random weights, and experimental results demonstrate the effectiveness of the proposed algorithm.展开更多
In this paper, performance of three classifiers for classification of five mental tasks were investigated. Wavelet Packet Transform (WPT) was used for feature extraction of the relevant frequency bands from raw Electr...In this paper, performance of three classifiers for classification of five mental tasks were investigated. Wavelet Packet Transform (WPT) was used for feature extraction of the relevant frequency bands from raw Electroencephalograph (EEG) signal. The three classifiers namely used were Multilayer Back propagation Neural Network, Support Vector Machine and Radial Basis Function Neural Network. In MLP-BP NN five training methods used were a) Gradient Descent Back Propagation b) Levenberg-Marquardt c) Resilient Back Propagation d) Conjugate Learning Gradient Back Propagation and e) Gradient Descent Back Propagation with movementum.展开更多
基金Project supported by the National Natural Science Foundation of China(Grant Nos.61471377,61804181,61604177,and 61704191).
文摘Vector neural network(VNN)is one of the most important methods to process interval data.However,the VNN,which contains a great number of multiply-accumulate(MAC)operations,often adopts pure numerical calculation method,and thus is difficult to be miniaturized for the embedded applications.In this paper,we propose a memristor based vector-type backpropagation(MVTBP)architecture which utilizes memristive arrays to accelerate the MAC operations of interval data.Owing to the unique brain-like synaptic characteristics of memristive devices,e.g.,small size,low power consumption,and high integration density,the proposed architecture can be implemented with low area and power consumption cost and easily applied to embedded systems.The simulation results indicate that the proposed architecture has better identification performance and noise tolerance.When the device precision is 6 bits and the error deviation level(EDL)is 20%,the proposed architecture can achieve an identification rate,which is about 92%higher than that for interval-value testing sample and 81%higher than that for scalar-value testing sample.
文摘Option pricing has become one of the quite important parts of the financial market. As the market is always dynamic, it is really difficult to predict the option price accurately. For this reason, various machine learning techniques have been designed and developed to deal with the problem of predicting the future trend of option price. In this paper, we compare the effectiveness of Support Vector Machine (SVM) and Artificial Neural Network (ANN) models for the prediction of option price. Both models are tested with a benchmark publicly available dataset namely SPY option price-2015 in both testing and training phases. The converted data through Principal Component Analysis (PCA) is used in both models to achieve better prediction accuracy. On the other hand, the entire dataset is partitioned into two groups of training (70%) and test sets (30%) to avoid overfitting problem. The outcomes of the SVM model are compared with those of the ANN model based on the root mean square errors (RMSE). It is demonstrated by the experimental results that the ANN model performs better than the SVM model, and the predicted option prices are in good agreement with the corresponding actual option prices.
文摘Accurate cost estimation at the early stage of a construction project is key factor in a project’s success. But it is difficult to quickly and accurately estimate construction costs at the planning stage, when drawings, documentation and the like are still incomplete. As such, various techniques have been applied to accurately estimate construction costs at an early stage, when project information is limited. While the various techniques have their pros and cons, there has been little effort made to determine the best technique in terms of cost estimating performance. The objective of this research is to compare the accuracy of three estimating techniques (regression analysis (RA), neural network (NN), and support vector machine techniques (SVM)) by performing estimations of construction costs. By comparing the accuracy of these techniques using historical cost data, it was found that NN model showed more accurate estimation results than the RA and SVM models. Consequently, it is determined that NN model is most suitable for estimating the cost of school building projects.
基金supported by the National Natural Science Foundation of China under Grant No. 60874088 and No. 11072059the Scientific Research Fund of Yunnan Province under Grant No. 2010ZC150the Scientific Research Fund of Yunnan Provincial Education Department under Grant No. 07Y10085
文摘In this article, we consider the global chaotic synchronization of general cou- pled neural networks, in which subsystems have both discrete and distributed delays. Stochastic perturbations between subsystems are also considered. On the basis of two sim- ple adaptive pinning feedback control schemes, Lyapunov functional method, and stochas- tic analysis approach, several sufficient conditions are developed to guarantee global syn- chronization of the coupled neural networks with two kinds of delay couplings, even if only partial states of the nodes are coupled. The outer-coupling matrices may be symmetric or asymmetric. Unlike existing results that an isolate node is introduced as the pinning target, we pin to help the network realizing synchronization without introducing any iso- late node when the network is not synchronized. As a by product, sufficient conditions under which the network realizes synchronization without control are derived. Numerical simulations confirm the effectiveness of the obtained results.
基金Supported by the National Natural Science Foundation of China (60573047), Natural Science Foundation of the Science and Technology Committee of Chongqing (8503) and the Applying Basic Research of the Education Committee of Chongqing (KJ060804)
文摘A new intrusion detection method based on learning vector quantization （LVQ） with low overhead and high efficiency is presented. The computer vision system employs LVQ neural networks as classifier to recognize intrusion. The recognition process includes three stages： （1） feature selection and data normalization processing;（2） learning the training data selected from the feature data set; （3） identifying the intrusion and generating the result report of machine condition classification. Experimental results show that the proposed method is promising in terms of detection accuracy, computational expense and implementation for intrusion detection.
文摘In this paper, sixty-eight research articles published between 2000 and 2017 as well as textbooks which employed four classification algorithms: K-Nearest-Neighbor (KNN), Support Vector Machines (SVM), Random Forest (RF) and Neural Network (NN) as the main statistical tools were reviewed. The aim was to examine and compare these nonparametric classification methods on the following attributes: robustness to training data, sensitivity to changes, data fitting, stability, ability to handle large data sizes, sensitivity to noise, time invested in parameter tuning, and accuracy. The performances, strengths and shortcomings of each of the algorithms were examined, and finally, a conclusion was arrived at on which one has higher performance. It was evident from the literature reviewed that RF is too sensitive to small changes in the training dataset and is occasionally unstable and tends to overfit in the model. KNN is easy to implement and understand but has a major drawback of becoming significantly slow as the size of the data in use grows, while the ideal value of K for the KNN classifier is difficult to set. SVM and RF are insensitive to noise or overtraining, which shows their ability in dealing with unbalanced data. Larger input datasets will lengthen classification times for NN and KNN more than for SVM and RF. Among these nonparametric classification methods, NN has the potential to become a more widely used classification algorithm, but because of their time-consuming parameter tuning procedure, high level of complexity in computational processing, the numerous types of NN architectures to choose from and the high number of algorithms used for training, most researchers recommend SVM and RF as easier and wieldy used methods which repeatedly achieve results with high accuracies and are often faster to implement.
基金supported by the National Scientific and Technological Task in China(Nos.2015BAD09B0101,2016YFD0600302)National Natural Science Foundation of China(No.31570619)the Special Science and Technology Innovation in Jiangxi Province(No.201702)
文摘Artificial neural network models are a popular estimation tool for fitting nonlinear relationships because they require no assumptions about the form of the fitting function,non-Gaussian distributions,multicollinearity,outliers and noise in the data.The problems of backpropagation models using artificial neural networks include determination of the structure of the network and overlearning courses.According to data from 1981 to 2008 from 15 permanent sample plots on Dagangshan Mountain in Jiangxi Province,a back-propagation artificial neural network model(BPANN)and a support vector machine model(SVM)for basal area of Chinese fir(Cunninghamia lanceolata)plantations were constructed using four kinds of prediction factors,including stand age,site index,surviving stem numbers and quadratic mean diameters.Artificial intelligence methods,especially SVM,could be effective in describing stand basal area growth of Chinese fir under different growth conditions with higher simulation precision than traditional regression models.SVM and the Chapman–Richards nonlinear mixed-effects model had less systematic bias than the BPANN.
基金supported by the National Natural Science Foundation of China(No.61074165 and No.61273064)Jilin Provincial Science&Technology Department Key Scientific and Technological Project(No.20140204034GX)Jilin Province Development and Reform Commission Project(No.2015Y043)
文摘Human body posture recognition has attracted considerable attention in recent years in wireless body area networks(WBAN). In order to precisely recognize human body posture,many recognition algorithms have been proposed.However, the recognition rate is relatively low. In this paper, we apply back propagation(BP) neural network as a classifier to recognizing human body posture, where signals are collected from VG350 acceleration sensor and a posture signal collection system based on WBAN is designed. Human body signal vector magnitude(SVM) and tri-axial acceleration sensor data are used to describe the human body postures. We are able to recognize 4postures: Walk, Run, Squat and Sit. Our posture recognition rate is up to 91.67%. Furthermore, we find an implied relationship between hidden layer neurons and the posture recognition rate. The proposed human body posture recognition algorithm lays the foundation for the subsequent applications.
文摘To make recommendation on items from the user for historical user rating several intelligent systems are using. The most common method is Recommendation systems. The main areas which play major roles are social networking, digital marketing, online shopping and E-commerce. Recommender system consists of several techniques for recommendations. Here we used the well known approach named as Collaborative filtering (CF). There are two types of problems mainly available with collaborative filtering. They are complete cold start (CCS) problem and incomplete cold start (ICS) problem. The authors proposed three novel methods such as collaborative filtering, and artificial neural networks and at last support vector machine to resolve CCS as well ICS problems. Based on the specific deep neural network SADE we can be able to remove the characteristics of products. By using sequential active of users and product characteristics we have the capability to adapt the cold start product ratings with the applications of the state of the art CF model, time SVD++. The proposed system consists of Netflix rating dataset which is used to perform the baseline techniques for rating prediction of cold start items. The calculation of two proposed recommendation techniques is compared on ICS items, and it is proved that it will be adaptable method. The proposed method can be able to transfer the products since cold start transfers to non-cold start status. Artificial Neural Network (ANN) is employed here to extract the item content features. One of the user preferences such as temporal dynamics is used to obtain the contented characteristics into predictions to overcome those problems. For the process of classification we have used linear support vector machine classifiers to receive the better performance when compared with the earlier methods.
文摘Protein Secondary Structure Prediction (PSSP) is considered as one of the major challenging tasks in bioinformatics, so many solutions have been proposed to solve that problem via trying to achieve more accurate prediction results. The goal of this paper is to develop and implement an intelligent based system to predict secondary structure of a protein from its primary amino acid sequence by using five models of Neural Network (NN). These models are Feed Forward Neural Network (FNN), Learning Vector Quantization (LVQ), Probabilistic Neural Network (PNN), Convolutional Neural Network (CNN), and CNN Fine Tuning for PSSP. To evaluate our approaches two datasets have been used. The first one contains 114 protein samples, and the second one contains 1845 protein samples.
文摘In order to solve the problems of small sample over-fitting and local minima when neural networks learn online, a novel method of predicting network bandwidth based on support vector machines(SVM) is proposed. The prediction and learning online will be completed by the proposed moving window learning algorithm(MWLA). The simulation research is done to validate the proposed method, which is compared with the method based on neural networks.
文摘External factors, such as social media and financial news, can have wide-spread effects on stock price movement. For this reason, social media is considered a useful resource for precise market predictions. In this paper, we show the effectiveness of using Twitter posts to predict stock prices. We start by training various models on the Sentiment 140 Twitter data. We found that Support Vector Machines (SVM) performed best (0.83 accuracy) in the sentimental analysis, so we used it to predict the average sentiment of tweets for each day that the market was open. Next, we use the sentimental analysis of one year’s data of tweets that contain the “stock market”, “stocktwits”, “AAPL” keywords, with the goal of predicting the corresponding stock prices of Apple Inc. (AAPL) and the US’s Dow Jones Industrial Average (DJIA) index prices. Two models, Boosted Regression Trees and Multilayer Perceptron Neural Networks were used to predict the closing price difference of AAPL and DJIA prices. We show that neural networks perform substantially better than traditional models for stocks’ price prediction.
文摘In the contemporary era, the proliferation of information technology has led to an unprecedented surge in data generation, with this data being dispersed across a multitude of mobile devices. Facing these situations and the training of deep learning model that needs great computing power support, the distributed algorithm that can carry out multi-party joint modeling has attracted everyone’s attention. The distributed training mode relieves the huge pressure of centralized model on computer computing power and communication. However, most distributed algorithms currently work in a master-slave mode, often including a central server for coordination, which to some extent will cause communication pressure, data leakage, privacy violations and other issues. To solve these problems, a decentralized fully distributed algorithm based on deep random weight neural network is proposed. The algorithm decomposes the original objective function into several sub-problems under consistency constraints, combines the decentralized average consensus (DAC) and alternating direction method of multipliers (ADMM), and achieves the goal of joint modeling and training through local calculation and communication of each node. Finally, we compare the proposed decentralized algorithm with several centralized deep neural networks with random weights, and experimental results demonstrate the effectiveness of the proposed algorithm.
文摘In this paper, performance of three classifiers for classification of five mental tasks were investigated. Wavelet Packet Transform (WPT) was used for feature extraction of the relevant frequency bands from raw Electroencephalograph (EEG) signal. The three classifiers namely used were Multilayer Back propagation Neural Network, Support Vector Machine and Radial Basis Function Neural Network. In MLP-BP NN five training methods used were a) Gradient Descent Back Propagation b) Levenberg-Marquardt c) Resilient Back Propagation d) Conjugate Learning Gradient Back Propagation and e) Gradient Descent Back Propagation with movementum.
