摘要
BP神经网络是一种多层前馈神经网络,主要的特点信号前向传播,误差是反向传播,从而构建其输入、输出的精准映射关系,并且泛化能力强,操作简便。运用BP神经网络对我国生活用纸产量进行了预测,拟合精度很高,网络的平均拟合误差仅为0.51506%。由此网络得到了2019-2023年我国生活用纸产量的预测值。
BP neural network is a kind of multi-layer feed forward neural network.Its main characteristics is that the signal propagates forward and the error propagates backward.Thus,the precise mapping relationship between input and output is constructed.It has strong generalization ability and is easy to operate,So BP neural network is used to predict the output of domestic paper in China with higher fitting accuracy.The average fitting error of the network is only 0.51506%,therefore The forecast value of domestic paper output in China from 2019 to 2013 can be obtained by the network.
作者
王艳
Wang Yan(School of Network Education of Wuhan University of Technology,Hubei,Wuhan 430070,China)
出处
《湖南涉外经济学院学报》
2020年第1期48-52,共5页
Journal of Hunan International Economics University
基金
湖北省自然科学基金(项目编号:2018CFB271)
关键词
生活用纸
产量
预测
神经网络
误差
反向传播
domestic paper
yield
prediction
Neural Network
error
back propagation