Research on BP Neural Network Algorithm Based on Quasi-Newton Method

2014 ◽  
Vol 686 ◽  
pp. 388-394 ◽  
Author(s):  
Pei Xin Lu
Keyword(s):  
Neural Network ◽  
Empirical Analysis ◽  
Newton Method ◽  
Bp Neural Network ◽  
Bp Algorithm ◽  
Newton Methods ◽  
Network Algorithm ◽  
Neural Network Algorithm ◽  
Quasi Newton ◽  
Improved Bp Algorithm

With more and more researches about improving BP algorithm, there are more improvement methods. The paper researches two improvement algorithms based on quasi-Newton method, DFP algorithm and L-BFGS algorithm. After fully analyzing the features of quasi-Newton methods, the paper improves BP neural network algorithm. And the adjustment is made for the problems in the improvement process. The paper makes empirical analysis and proves the effectiveness of BP neural network algorithm based on quasi-Newton method. The improved algorithms are compared with the traditional BP algorithm, which indicates that the improved BP algorithm is better.

Research on the Improvement of BP Neural Network Algorithm and its Application

2014 ◽  
Vol 926-930 ◽  
pp. 3216-3219 ◽  
Author(s):  
Xiong Kai
Keyword(s):  
Neural Network ◽  
Optimization Algorithm ◽  
Bp Neural Network ◽  
Bp Algorithm ◽  
Network Algorithm ◽  
Simulation Calculation ◽  
Neural Network Algorithm ◽  
Working Principle ◽  
Calculation Ability ◽  
Improved Bp Algorithm

BP neural network has excellent ability to solve nonlinear optimal problem for its powerful simulation calculation ability and is wildly used in various disciplines in recent years, but its shortages of low convergence speed and falling into local minimum easily limit the usage of the algorithm. Based on the Levenberg-Marqardt optimization algorithm, the paper improves the BP neural network to overcome its shortages. First, the working structure and shortages of BP neural network are analyzed with more details. Second, the working principle of BP neural network algorithm is improved with Levenberg-Marqardt optimization algorithm and the calculation flows is redesigned. Third, data from three universities are used to realize the improved algorithm and the experimental results shows that the improved BP algorithm has better performance in calculation time and evaluation accuracy when used in university classroom teaching evaluation practically.

Study on PCA-Based BP Neural Network Algorithm

2014 ◽  
Vol 530-531 ◽  
pp. 517-521
Author(s):  
Jian Qing Hong ◽  
De'an Zhao ◽  
Wei Kuan Jia
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Computing Time ◽  
Principal Component ◽  
Bp Algorithm ◽  
Complex Data ◽  
Network Algorithm ◽  
The Neural Network ◽  
Neural Network Algorithm ◽  
Low Dimensional

Using the neural network to deal with complex data, because the pending sample with many variables, aiming at this nature of the pending sample and the structure properties of the BP neural network, in this paper, we propose the new BP neural network algorithm base on principal component analysis (PCA-BP algorithm). The new algorithm through PCA dimension reduction for complex data, got the low-dimensional data as the BP neural networks input, it will be beneficial to design the hidden layer of neural network, save a lot of storage space and computing time, and conductive to the convergence of the neural network. In order to verify the validity of the new algorithm, compared with the traditional BP algorithm, through the case analysis, the result show that the new algorithm improve the efficiency and recognition precise, worthy of further promotion.

Research of Orange Quality Classification Technology Based on BP Neural Network Algorithm

2015 ◽  
Vol 713-715 ◽  
pp. 1821-1824
Author(s):  
Chun Hua Qian ◽  
He Qun Qiang ◽  
Sheng Rong Gong
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Classification Accuracy ◽  
Bp Algorithm ◽  
Shape Features ◽  
Accuracy Rate ◽  
Network Algorithm ◽  
Quality Classification ◽  
Neural Network Algorithm

BP algorithm is a classical neural network algorithm. We analyzed the deficiency of traditional BP neural network algorithm, designed new S function and momentum method strategy, optimized the algorithm parameters. We use the new algorithm in the classification of orange images, take color and shape features as input value, the experimental results proved that our algorithm is faster and the classification accuracy rate reaches to 90%

An Improved BP Neural Network Algorithm and its Application

2014 ◽  
Vol 543-547 ◽  
pp. 2120-2123 ◽  
Author(s):  
Ming Jun Chen
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Ant Colony Algorithm ◽  
Back Propagation ◽  
Indicator System ◽  
Global Optimum ◽  
Bp Algorithm ◽  
Nonlinear Simulation ◽  
Network Algorithm ◽  
Neural Network Algorithm

Back-propagation (BP) neural network algorithm is currently used most widely and grows fastest for its powful nonlinear simulation capability. However BP neural network is so easy to fall into local minima that it cant find the global optimum which limits its application in many fields. The paper, taking tax innovation teaching evaluation for example, advances a new evaluation algorithm based on improved BP neural network algorithm. Firstly an evaluation indicator system of tax major innovation teaching is designed through analyzing the specific characteristics of innovation teaching requirements. Secondly, in order to overcome the shortages of low convergence speed of original BP neural network algorithm, the paper improves BP algorithm through integrating BP algorithm and ant colony algorithm, ant improving the overall search method of integrated algorithm. Thirdly data from three universities are taken for examples to verify the validity and feasibility of the model and the experimental results show that the model can evaluate university innovation teaching practically.

scholarly journals Information System Security Evaluation Algorithm Based on PSO-BP Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Qinghua Zheng
Keyword(s):  
Neural Network ◽  
Information System ◽  
Bp Neural Network ◽  
System Security ◽  
Bp Algorithm ◽  
Security Evaluation ◽  
Information System Security ◽  
The Core ◽  
Network Algorithm ◽  
Neural Network Algorithm

With the deepening of big data and the development of information technology, the country, enterprises, organizations, and even individuals are more and more dependent on the information system. In recent years, all kinds of network attacks emerge in an endless stream, and the losses are immeasurable. Therefore, the protection of information system security is a problem that needs to be paid attention to in the new situation. The existing BP neural network algorithm is improved as the core algorithm of the security intelligent evaluation of the rating information system. The input nodes are optimized. In the risk factor identification stage, most redundant information is filtered out and the core factors are extracted. In the risk establishment stage, the particle swarm optimization algorithm is used to optimize the initial network parameters of BP neural network algorithm to overcome the dependence of the network on the initial threshold, At the same time, the performance of the improved algorithm is verified by simulation experiments. The experimental results show that compared with the traditional BP algorithm, PSO-BP algorithm has faster convergence speed and higher accuracy in risk value prediction. The error value of PSO-BP evaluation method is almost zero, and there is no error fluctuation in 100 sample tests. The maximum error value is only 0.34 and the average error value is 0.21, which proves that PSO-BP algorithm has excellent performance.

Research on Intelligent Control Technology with Building Energy Control Model Based on Intelligent Control Algorithm

2014 ◽  
Vol 1014 ◽  
pp. 329-332
Author(s):  
Wei Ping Wang ◽  
Li Zhou
Keyword(s):  
Neural Network ◽  
Intelligent Control ◽  
Bp Neural Network ◽  
Fuzzy Neural Network ◽  
Building Energy ◽  
Energy Control ◽  
Network Algorithm ◽  
Fuzzy Neural ◽  
Neural Network Algorithm ◽  
Improved Bp Algorithm

For the current smart building energy control algorithms are still large energy loss, poor energy-saving effect and other issues, this paper presents a fuzzy neural network algorithm based on improved BP algorithm, the improved algorithm of BP neural network algorithm first reverse dissemination and weighting coefficients are adjusted to accelerate the convergence rate of the original algorithm, and then build the improved BP neural network algorithm for fuzzy neural network, and then to improve it fuzzy membership function parameters to improve the efficiency of fuzzy neural network learning. Simulation results show that the proposed fuzzy neural network algorithm based on improved BP algorithm in the intelligent building energy control, with the algorithm is better than traditional BP neural network energy savings, reducing the energy loss rate.

A time simulated annealing-back propagation algorithm and its application in disease prediction

2018 ◽  
Vol 32 (25) ◽  
pp. 1850303 ◽  
Author(s):  
Fang Hu ◽  
Mingzhu Wang ◽  
Yanhui Zhu ◽  
Jia Liu ◽  
Yalin Jia
Keyword(s):  
Neural Network ◽  
Simulated Annealing ◽  
Bp Neural Network ◽  
Back Propagation ◽  
Bp Algorithm ◽  
Disease Prediction ◽  
Back Propagation Algorithm ◽  
Network Algorithm ◽  
Learning Rates ◽  
Neural Network Algorithm

In this paper, based on the Back Propagation (BP) neural network algorithm, we introduce the idea of the Simulated Annealing (SA), and then propose a new neural network algorithm: Time Simulated Annealing-Back Propagation (TSA-BP) algorithm. The proposed algorithm can improve the convergence rate and numerical stability. By using this proposed algorithm, the learning rates and initial weights in the BP neural network could be easily adjusted. We show that the TSA-BP algorithm could reduce the errors caused by human-made factors. Several numerical experiments have been tested by using different disease data. Furthermore, we compared the TSA-BP algorithm to the other existing, well-known algorithms. Numerical results show higher accuracy and efficiency of the TSA-BP algorithm.

Sign in / Sign up

Export Citation Format

Share Document