摘要
针对BP人工神经网络的结构特性,提出了将自组织理论与BP人工神经网络相结合的思想,不仅解决了输入待定的神经网络输入维数难确定的问题,而且加快了神经网络的收敛速度,增强了神经网络的适应能力.并将新建立的模型应用到税收预测中,得出了比常规经济学模型更优的效果.
In this paper, aiming at the characteristics of BP neural network structure, a method of connecting GMDH and BP neural network is presented. It can make the selection of input-lay units easily, and improve the adaptability and convergence rate of neural network. Then we apply it to tax forecasting, our conclusion shows that this method is superior to the statistical modeling approach.
出处
《数学的实践与认识》
CSCD
北大核心
2006年第7期251-255,共5页
Mathematics in Practice and Theory
