An Improved BP Algorithm Based on Steepness Factor and Adaptive Learning Rate Adjustment Factor

Abstract:

BP network is the most widely used of the neural net work model, but there are many problems of slow convergence speed and easily getting into the local minimum in the conventional BP algorithm. For this, an improved algorithm is proposed. Momentum term is added, steepness factors are introduced and adaptive learning rate adjustment factor is added. In the Matlab platform simulations are carried out by each improvement methods on the same BP neural network. The results show that: Convergence of improved BP network is decreased from 1000 to 49 and the error is decreased from 10-2 to 10-6. The convergence speed has been significantly improved and the error has been decreased. Using the synthesis improvement method effect is obvious and it provides a good theoretical basis for the practical application.

• Periodical: Applied Mechanics and Materials (Volumes 121-126)
• Pages: 705-709
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.121-126.705
• Online since: October 2011
• Authors: Xiu Hua Zhang, Fu Jun Ren, Yong Cheng Jiang
• Keywords: Adaptive Learning Rate, BP Algorithm, Momentum, Steepness Factor

References

[1] Liqun Han: Artificial Neural Network Theory, Design and Applications (Chemical Industry Press, Beijing 2007), in Chinese.

[2] Zengqiang Chen, Zhuzhi Yuan, Yan Zhang et al.: A Survey on Neural-Network Based Nonlinear Predictive Control Vol. 4(2002), pp.35-38.

[3] Zhong Luo, Wenbi Rao, Chengming Zou et al.: Artificial Neural Network and Technology of Fusion and Application (Science Press, Beijing 2007), in Chinese.

[4] Kaili Zhou, Yaohong Kang: Neural Network and Its Simulation Program Design Based on MATLAB(TSINGHUA UNIVERSITY PRESS, Beijing 2006), in Chinese.

[5] Hemmateenejad B, Akhond M, Miri R: Genetic Algorithm Applied to the Selection of Factors in Principal Component-Artificial Neural Networks Vol. 43(2007), pp.1328-1334.

DOI: 10.1021/ci025661p

[6] Shamsipur M, Hemmateenejad B, Akhond M: Multicomponent Acid-Base Titration by Principal Component-Artificial Neural Network Vol. 461(2002), pp.147-153.

DOI: 10.1016/s0003-2670(02)00236-2

[7] Jianfeng Li, Yifen Shi: BP improvement algorithm and application Vol. 21(1995). pp.62-66.

[8] Hailan Yang, Yixiong Wu. PCA-based ANN for arc welding quality control Vol. 4(2003), pp.33-58.

[9] Bo Yang, Yadong Wang, Xiaohong Su et al.: An Algorithm for Fast Convergence of Back Propagation by Enlarging Error Vol. 41(2004), pp.774-779.

[10] Jicheng Zhou: Artificial Neural Network (Popular Science Press, Beijing 1992), in Chinese.