Curvature-based BP Algorithm Optimization and Its Application in FNN

Authors

Weili Xiong, 1. School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China;;2. Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi 214122, China;
Wenxin Sun, 1. School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China;;
Xudong Shi, 1. School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China;;

Abstract

Abstract: In order to improve the optimization efficiency of BP algorithm affected by the selection of step size, a step size optimization BP algorithm based on curvature information is proposed and applied to the training process of FNN (Fuzzy Neural Network). Reference to Newton's method, The gradient of the cost function and the curvature information in the direction are calculated to determine the direction and magnitude of the parameter adjustment in each iteration. This method only needs to consider the two order information of the gradient direction, so it does not need the storage and processing of Hessian matrix. The effectiveness and efficiency of the proposed method are verified by a numerical simulation and data simulation of blast furnace ironmaking process.

Recommended Citation

Xiong, Weili; Sun, Wenxin; and Shi, Xudong (2020) "Curvature-based BP Algorithm Optimization and Its Application in FNN," Journal of System Simulation: Vol. 32: Iss. 1, Article 1.
DOI: 10.16182/j.issn1004731x.joss.17-0461
Available at: https://dc-china-simulation.researchcommons.org/journal/vol32/iss1/1

First Page

1

Revised Date

2018-01-18

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.17-0461

Last Page

8

CLC

TP183

Recommended Citation

Xiong Weili, Sun Wenxin, Shi Xudong. Curvature-based BP Algorithm Optimization and Its Application in FNN[J]. Journal of System Simulation, 2020, 32(1): 1-8.

DOI

10.16182/j.issn1004731x.joss.17-0461