• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Mathematical Problems in Engineering >A Joint Optimization of Momentum Item and Levenberg-Marquardt Algorithm to Level Up the BPNN's Generalization Ability
【24h】

A Joint Optimization of Momentum Item and Levenberg-Marquardt Algorithm to Level Up the BPNN's Generalization Ability

机译：动量项和Levenberg-Marquardt算法的联合优化以提升BPNN的泛化能力

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Back propagation neural network (BPNN) as a kind of artificial neural network is widely used in pattern recognition and trend prediction. For standard BPNN, it has many drawbacks such as trapping into local optima, oscillation, and long training time. Because training the standard BPNN is based on gradient descent method, and the learning rate is fixed. Momentum item and Levenberg-Marquardt (LM) algorithm are two ways to adjust the weights among the neurons and improve the BPNN's performance. However, there is still much space to improve the two algorithms. The hybrid optimization of damping factor of LM and the dynamic momentum item is proposed in this paper. The improved BPNN is validated by Fisher Iris data and wine data. Then, it is used to predict the visit_spend. The database is provided by Dunnhumby's Shopper Challenge. Compared with the other two improved BPNNs, the proposed method gets a better performance. Therefore, the proposed method can be used to do the pattern recognition and time series prediction more effectively.
机译：反向传播神经网络（BPNN）作为一种人工神经网络，被广泛应用于模式识别和趋势预测。对于标准BPNN，它具有许多缺点，例如陷入局部最优，振荡和训练时间长。由于训练标准BPNN是基于梯度下降法的，因此学习率是固定的。动量项和Levenberg-Marquardt（LM）算法是调整神经元之间的权重并提高BPNN性能的两种方法。但是，仍然有很多空间可以改进这两种算法。提出了LM阻尼系数与动量项的混合优化方法。改进的BPNN已通过Fisher Iris数据和葡萄酒数据进行了验证。然后，将其用于预测visit_spend。该数据库由Dunnhumby的购物者挑战赛提供。与其他两个改进的BPNN相比，该方法具有更好的性能。因此，该方法可用于更有效地进行模式识别和时间序列预测。

著录项

  • 来源
    《Mathematical Problems in Engineering》 |2014年第8期|653072.1-653072.10|共10页
  • 作者

    Lei Xiao; Xiaohui Chen; Xinghui Zhang;

  • 作者单位

    The State Key Lab of Mechanical Transmission, Chongqing University, Chongqing 400030, China;

    The State Key Lab of Mechanical Transmission, Chongqing University, Chongqing 400030, China;

    Mechanical Engineering College, Shijiazhuang 050003, China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号