首页> 外文期刊>Mathematical Problems in Engineering >Research and Application of Improved AGP Algorithm for Structural Optimization Based on Feedforward Neural Networks
【24h】

Research and Application of Improved AGP Algorithm for Structural Optimization Based on Feedforward Neural Networks

机译:基于前馈神经网络的改进AGP算法在结构优化中的研究与应用

获取原文
获取原文并翻译 | 示例
           

摘要

The adaptive growing and pruning algorithm (AGP) has been improved, and the network pruning is based on the sigmoidal activation value of the node and all the weights of its outgoing connections. The nodes are pruned directly, but those nodes that have internal relation are not removed. The network growing is based on the idea of variance. We directly copy those nodes with high correlation. An improved AGP algorithm (IAGP) is proposed. And it improves the network performance and efficiency. The simulation results show that, compared with the AGP algorithm, the improved method (IAGP) can quickly and accurately predict traffic capacity.
机译:改进了自适应增长和修剪算法(AGP),并且网络修剪是基于节点的S型激活值及其出站连接的所有权重。将直接修剪节点,但不会删除具有内部关系的那些节点。网络的增长是基于方差的思想。我们直接复制那些具有高相关性的节点。提出了一种改进的AGP算法(IAGP)。并提高了网络性能和效率。仿真结果表明,与AGP算法相比,改进后的方法(IAGP)可以快速,准确地预测流量。

著录项

  • 来源
    《Mathematical Problems in Engineering》 |2015年第7期|481919.1-481919.6|共6页
  • 作者单位

    Guangxi Teachers Educ Univ, Comp & Informat Engn Coll, Nanning 530023, Peoples R China.;

    Guangxi Teachers Educ Univ, Comp & Informat Engn Coll, Nanning 530023, Peoples R China.;

    Guangxi Teachers Educ Univ, Comp & Informat Engn Coll, Nanning 530023, Peoples R China.;

    Guangxi Teachers Educ Univ, Comp & Informat Engn Coll, Nanning 530023, Peoples R 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