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

Abstract:

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.

• Periodical: Applied Mechanics and Materials (Volume 686)
• Pages: 388-394
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.686.388
• Online since: October 2014
• Authors: Pei Xin Lu*
• Keywords: BP Neural Network, Improved Algorithm, Newton Method

References

[1] Liu Bo, Shi Xiuzhi, Huang Xuandong, Wu Yongmeng, Huang Dan, Luo Jia, QN-BP predicting vibration speed based on quasi-Newton method [J], China Non-Ferrous Metal Journal, 2013, 05: 1427-1433.

[2] Fan Wengao, Tian Luoping, Wang Xiaohong, Establishing neural network model of CRT color conversion [J],  Optoelectronic Enginneering, 2006, 05: 118-121.

[3] Jiao Aiping, He Jiang, Neural network model of bedrock balance depth prediction [J], People Yellow River, 2007, 06: 55-56.

[4] Zhang Chiping, Tang Lei, Su Xiaohong, Ma Peijun, Improved DEP neural network learning algorithm [J], Computer Simulation, 2008, 04: 172-174+209.

[5] Lin Lin, Huang Nantian, Gao Xingquan,  Fourier neural network based on DFP quasi-Newton method [J], Computer Engineering, 2012, 10: 144-147.

[6] Lu Peixin , 7 Floor, Kunxun Building, No. 9, Zhichun Road, Haidian District, Beijing, China.