摘要
提出一种等比例系数型BP神经网络权值和阈值的初始化方法,该方法可将S型传递函数的自变量转化到区间[0,1)上,从而提高网络的收敛性能.从理论上证明了该方法的可行,并通过非线性函数y=x12+x22的拟合实验,证明了该方法是有效的.
The paper presents an initialized method of equal-scaling coefficient type based on BP neural network weights and thresholds, which can convert the independent variable of sigmoid transfer function to the interval I0,1 ）, thereby improving the convergence performance of the network. It is theoretically proved that the method is feasible, and it shows that the method is effective proved by fitting experiments on the non-linear functiony=xl2＋X22.
出处
《韶关学院学报》
2013年第12期18-21,共4页
Journal of Shaoguan University
基金
宁德师范学院"服务海西建设"项目(2012H406)
关键词
BP神经网络
权值
阈值
初始化
BP neural network
weights
threshold
initialization
