摘要
该文讨论了BP神经网络和共轭梯度算法以及用改进的共轭梯度BP神经网络进行药品销售量预测。分别用二种方法对药品销售进行预测。仿真结果表明,BP神经网络训练时间长,预测精度低;而共轭梯度算法改进BP神经网络不仅缩短了网络训练时间,而且提高了模型的预测精度。实例证明该方法可行,可用于药品销售预测。
This paper discussed the BP neural network,the conjugate gradient algorithm to improve BP neural network algorithm and the improved BP neural network for prediction of the drug sales.And the simulation results of two kinds of prediction method were given.Ac cording to the simulation results that the BP neural network training time is longer and the prediction precision is lower,but the improved BP neural network algorithm with Conjugate gradient algorithm makes the training times shorter,and it enhances prediction precision.The calculation results show that the approaches of the improved BP neural network with conjugate gradient algorithm is feasible and can be used for prediction of drug sales.
出处
《电脑知识与技术（过刊）》
2012年第5X期3361-3363,3370,共4页
Computer Knowledge and Technology
基金
中国科学院华南植物园横向委托项目:基于数据挖掘技术的珍稀名贵树种种质资源库管理信息系统以及决策支持系统的分析和设计
关键词
BP神经网络
共轭梯度法
销售预测
BP neural network
conjugate gradient algorithm
prediction of the drug sales
