期刊名称：IOP Conference Series: Earth and Environmental Science
印刷版ISSN：1755-1307
电子版ISSN：1755-1315
出版年度：2019
卷号：310
期号：2
页码：1-7
DOI：10.1088/1755-1315/310/2/022036
出版社：IOP Publishing
摘要：According to the accuracy of BP (Back Propagation) neural network in leveling fitting, an improved BP neural network model is proposed. In order to overcome the defect of the low convergence rate and local minimal in leveling fitting. The BP neural network is improved by using Relu (Rectified Linear Units) function as network activation function and Adam (Adaptive Moment Estimation) algorithm as network optimization function. The experimental results show that the improved BP neural network can effectively improve the accuracy.
