• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Mathematical Problems in Engineering >Weight Optimization in Recurrent Neural Networks with Hybrid Metaheuristic Cuckoo Search Techniques for Data Classification
【24h】

Weight Optimization in Recurrent Neural Networks with Hybrid Metaheuristic Cuckoo Search Techniques for Data Classification

机译：基于混合元启发式布谷鸟搜索技术的递归神经网络权重优化

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

Recurrent neural network (RNN) has been widely used as a tool in the data classification. This network can be educated with gradient descent back propagation. However, traditional training algorithms have some drawbacks such as slow speed of convergence being not definite to find the global minimum of the error function since gradient descent may get stuck in local minima. As a solution, nature inspired metaheuristic algorithms provide derivative-free solution to optimize complex problems. This paper proposes a new metaheuristic search algorithm called Cuckoo Search (CS) based on Cuckoo bird's behavior to train Elman recurrent network (ERN) and back propagation Elman recurrent network (BPERN) in achieving fast convergence rate and to avoid local minima problem. The proposed CSERN and CSBPERN algorithms are compared with artificial bee colony using BP algorithm and other hybrid variants algorithms. Specifically, some selected benchmark classification problems are used. The simulation results show that the computational efficiency of ERN and BPERN training process is highly enhanced when coupled with the proposed hybrid method.
机译：递归神经网络（RNN）已被广泛用作数据分类的工具。该网络可以通过梯度下降反向传播进行教育。但是，传统的训练算法具有一些缺点，例如，由于梯度下降可能会卡在局部最小值中，因此收敛速度缓慢并不确定，无法找到误差函数的全局最小值。作为一种解决方案，自然启发式元启发式算法提供了无导数解决方案来优化复杂问题。本文提出了一种基于杜鹃鸟的行为的新的启发式搜索算法，称为杜鹃搜索（CS），以训练Elman递归网络（ERN）和反向传播Elman递归网络（BPERN）来实现快速收敛速度和避免局部极小问题。提出的CSERN和CSBPERN算法与使用BP算法和其他混合变体算法的人工蜂群进行了比较。具体来说，使用一些选定的基准分类问题。仿真结果表明，与提出的混合方法相结合，可以极大地提高ERN和BPERN训练过程的计算效率。

著录项

  • 来源
    《Mathematical Problems in Engineering》 |2015年第19期|868375.1-868375.12|共12页
  • 作者

    Nawi Nazri Mohd; Khan Abdullah; Rehman M. Z.; Chiroma Haruna; Herawan Tutut;

  • 作者单位

    Univ Tun Hussein Onn Malaysia, Fac Comp Sci & Informat Technol, Software & Multimedia Ctr, Batu Pahat 86400, Johor, Malaysia;

    Univ Tun Hussein Onn Malaysia, Fac Comp Sci & Informat Technol, Software & Multimedia Ctr, Batu Pahat 86400, Johor, Malaysia;

    Univ Tun Hussein Onn Malaysia, Fac Comp Sci & Informat Technol, Software & Multimedia Ctr, Batu Pahat 86400, Johor, Malaysia;

    Univ Malaya, Dept Artificial Intelligence, Kuala Lumpur 50603, Malaysia;

    Univ Malaya, Dept Informat Syst, Kuala Lumpur 50603, Malaysia;

  • 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