Due to the explosive increment of data in big data era, it is a challenging task to analyze and extract meaningful data for users. Data needs to be timely operated because of the time sensitivity, so it faces enormous...
详细信息
ISBN:
(纸本)9781479920037
Due to the explosive increment of data in big data era, it is a challenging task to analyze and extract meaningful data for users. Data needs to be timely operated because of the time sensitivity, so it faces enormous pressure in storage and computing. To deal with the problem that it is hard to achieve valuable information from out-of-order streams over big data in short time, a model-matching algorithm based on improved bp (Back Propagation) is proposed. In the algorithm, the matching model is set dynamically. Information is extracted for users according to the order of data's arriving time. Furthermore, the algorithm parameters are automatically adjusted in the process of learning and matching. Accordingly, the responding speed of learning is accelerated and the time of matching reduces. In the simulation, a group of optimum parameters of improved bp are achieved by using self-adapting adjusting mechanism. The threshold (TH), connecting weight (CW) and learning rate (LR) are equal to 1.5, 3 and 1, respectively. We implement our model-matching algorithm on 10000 sets of out-of-order streams with these parameters. Results indicate that the proposed algorithm can obviously improve the accuracy and speed of matching and achieve better stability.
Neural network is widely used in pattern recognition, image processing and system control. bp neural network has its inherent deficiencies. Its convergence rate is slow. It is easy to fall into the local minimum and t...
详细信息
ISBN:
(纸本)9780769538044
Neural network is widely used in pattern recognition, image processing and system control. bp neural network has its inherent deficiencies. Its convergence rate is slow. It is easy to fall into the local minimum and the structure of the neural network is hard to determine. The structure of hidden layer is determined through the experience, but it can not make accurate judgments with complex network structure. In order to improve the function of the bp neural network, an improved algorithm of bp neural network based on the standard sigmoid function is put forward. Fuzzy theory is added to the algorithm to determine the structure of hidden layer and dynamically adjusted additional momentum factor is also added. Compare with conventional algorithms it has a greater ability to enhance the study, reduce the hidden layers' nodes effectively, and it also has a higher network convergence speed and precision.
The bp neural network algorithm is improved to detect intrusion. The improved method is as follows: according to different input, different part of network will be fired to generate output. The weights of the arcs onl...
详细信息
The bp neural network algorithm is improved to detect intrusion. The improved method is as follows: according to different input, different part of network will be fired to generate output. The weights of the arcs only connected with fired neuron will be adjusted whereas all weights in traditional bp network must be adjusted. The experiment results indicate that this improved algorithm can increase learning speed and shorten training time. The results also show that the intrusion detection rate is improved.
A uniformly most powerful(UMP) belief propagation(bp) based algorithm is referred to as a simplified version of a bp algorithm with reduced complexity but performance loss for low density parity check(LDPC) *** compen...
详细信息
A uniformly most powerful(UMP) belief propagation(bp) based algorithm is referred to as a simplified version of a bp algorithm with reduced complexity but performance loss for low density parity check(LDPC) *** compensate the performance loss,the normalized bp based algorithm was proposed,where the normalization factor was derived by mean ratio or by minimizing the mean square *** this paper,an improved novel normalized bp based algorithm is *** normalization uses multiplicative factor instead of divisional *** novel scheme shows better performance than the existing normalized bp based algorithms while keeping the same implementation *** simulation is done for two kinds of LDPC codes:random constructed codes and finite geometry codes. At high signal-to-noise ratio(SNR) region,the proposed scheme can achieve even better performance than bp algorithm for short length random constructed LDPC codes.
The genetic algorithm is a new random search algorithm based on natural selection and the principle of gene genetics. As the back propagation algorithm has some shortages, such as low efficiency of le
The genetic algorithm is a new random search algorithm based on natural selection and the principle of gene genetics. As the back propagation algorithm has some shortages, such as low efficiency of le
The back-propagation algorithm(bp) is a wellknown method of training a multilayer Feed -Forward Artificial Neural Networks(FFANNS).Although the algorithm is successful,it has some disadvantages. Because of adopting th...
详细信息
The back-propagation algorithm(bp) is a wellknown method of training a multilayer Feed -Forward Artificial Neural Networks(FFANNS).Although the algorithm is successful,it has some disadvantages. Because of adopting the gradient method by bp neural network,the problems including slowly learning convergent velocity and easily converging to local minimum can not be *** addition,the selection of learning factor and inertial factor affects the convergence of bp neural network,which are usually determined by *** the effective application of bp neural network is limited. In this paper a new method in bp algorithm to avoid local minimum was proposed by means of adding gradually training data and hidden *** addition, the paper also proposed a new model of controllable feed-forward neural network.
Traditional bp algorithm has the advantages of simple plastic, but there are easy to fall into local extremum, unable to overcome the defects such as slow convergence speed. The particle swarm optimization(PSO) algori...
详细信息
Traditional bp algorithm has the advantages of simple plastic, but there are easy to fall into local extremum, unable to overcome the defects such as slow convergence speed. The particle swarm optimization(PSO) algorithm has the advantages of short training time, small relative error and high control precision. Therefore, this paper designs an modified particle swam optimization algorithm to optimize the bp neural network method, for measuring oil-water interface problem in the process of dehydration of crude oil production, related soft-sensing model is established and simulated experiment, verify the correctness of the model.
The reliability growth prediction is a most important part of the reliability engineering. The artificial neural network is a new subject developed in recent years. This paper presents the reliability growth and bp al...
详细信息
ISBN:
(纸本)7312012035
The reliability growth prediction is a most important part of the reliability engineering. The artificial neural network is a new subject developed in recent years. This paper presents the reliability growth and bp algorithm, then considers emphatically bp algorithm application in the reliability growth prediction. Gompertz model is a better model of the reliability growth models, the paper examines the algorithm by some instances and compares with results of Gompertz model, and results are basically consistent. It shows the approach is feasible, effective, simple, and adaptive. The reliability storage in the weapon system is negative growth;this paper also discusses the prediction of the reliability storage in the weapon system using the bp algorithm.
In the artificial neural network,bp neural network is a multilayer feedforward neural network which is used *** neural network uses a classic bp algorithm,and it is in accordance with the error back-propagation algori...
详细信息
In the artificial neural network,bp neural network is a multilayer feedforward neural network which is used *** neural network uses a classic bp algorithm,and it is in accordance with the error back-propagation algorithm for learning and *** paper first analyzes the basic idea of bp algorithm,and using bp neural network model and the flow chart to illustrate;then,introduces the disadvantage of bp algorithm,has slow convergence and easy to fall into local minimum point and other defects,and describes the current improvements methods,such as adding momentum item,introduce variable step method and other optimization methods,which effectively improve the convergence of bp algorithm,to avoid falling into local minimum point;finally,describes in detail the application of bp neural network in face *** research on bp neural network,which can be further development and application of bp networks play an important role.
暂无评论