Computer Engineering and Applications ›› 2008, Vol. 44 ›› Issue (14): 246-248.

• 工程与应用 • Previous Articles    

Neural network prediction model based on differential evolution algorithm and its application

YU Qing1,2,ZHAO Hui3   

  1. 1.School of Computer Science and Technology,Tianjin University of Technology,Tianjin 300191,China
    2.Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology,Tianjin 300191,China
    3.Economics and Management College,CAUC,Tianjin 300300,China
  • Received:2007-12-06 Revised:2008-02-27 Online:2008-05-11 Published:2008-05-11
  • Contact: YU Qing


于 青1,2,赵 辉3   

  1. 1.天津理工大学 计算机科学与技术学院,天津 300191
    2.天津市智能计算及软件新技术重点实验室,天津 300191
    3.中国民航大学 经济与管理学院,天津 300300
  • 通讯作者: 于 青

Abstract: Structural designing of artificial network is always a trouble problem without systematic rule and local minimum usually connects with conventional grads based on parameters optimization.Aiming at the drawback in classical BP artificial networks and combining with differential evolution algorithms,this paper puts forwards the prediction model based on real number coded DE-BP artificial networks.This model achieves satisfactory results on tax forecasting.

Key words: Differential Evolution(DE), neural network, prediction, real-coded

摘要: 人工神经网络的结构设计没有系统的规律可遵循,而常用的基于梯度的神经网络参数优化又易陷入局部最优解。针对BP人工神经网络所存在的缺陷,结合差异演化算法,提出了实数编码的DE-BP神经网络预测模型。利用税收预测的实例验证了算法的有效性,取得了令人满意的结果。

关键词: 差异演化算法, 神经网络, 预测, 实数编码