• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文学位 >Second order training algorithms for radial basis function neural network.
【24h】

Second order training algorithms for radial basis function neural network.

机译：径向基函数神经网络的二阶训练算法。

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

A systematic two step batch approach for constructing and training of Radial basis function (RBF) neural networks is presented. Unlike other RBF learning algorithms, the proposed paradigm uses optimal learning factors (OLF's) to train the network parameters, i.e. spread parameters, mean vector parameters and weighted distance measure (DM) coefficients. Newton's algorithm is proposed for obtaining multiple optimal learning factors (MOLF) for the network parameters. The weights connected to the output layer are trained by a supervised-learning algorithm based on orthogonal least squares (OLS). The error obtained is then back-propagated to tune the RBF parameters. The proposed hybrid training algorithm has been compared with the Levenberg Marquardt and recursive least square based RLS-RBF training algorithms. Simulation results show that regardless of the input data dimension, the proposed algorithms are a significant improvement in terms of convergence speed, network size and generalization over conventional RBF training algorithms which use a single optimal learning factor (SOLF). Analyses of the proposed training algorithms on noisy input data have also been carried out. The ability of the proposed algorithm is further substantiated by using k-fold cross validation. Initialization of network parameters using Self Organizing Map (SOM), efficient calculation of Hessian matrix for network parameters, Newton's method for optimization, optimal learning factors and orthogonal least squares are the subject matter of present work.
机译：提出了一种用于径向基函数（RBF）神经网络的构建和训练的系统两步批处理方法。与其他RBF学习算法不同，本文提出的范例使用最佳学习因子（OLF）来训练网络参数，即扩展参数，平均矢量参数和加权距离度量（DM）系数。提出了牛顿算法来获取网络参数的多个最优学习因子（MOLF）。通过基于正交最小二乘（OLS）的监督学习算法来训练连接到输出层的权重。然后，将获得的误差反向传播以调整RBF参数。所提出的混合训练算法已与Levenberg Marquardt和基于递归最小二乘的RLS-RBF训练算法进行了比较。仿真结果表明，与使用单个最佳学习因子（SOLF）的常规RBF训练算法相比，无论输入数据维数如何，所提出的算法在收敛速度，网络大小和泛化方面均具有显着改进。还对提出的针对嘈杂输入数据的训练算法进行了分析。通过使用k倍交叉验证进一步证实了所提出算法的能力。使用自组织映射（SOM）初始化网络参数，有效计算网络参数的Hessian矩阵，牛顿优化方法，最佳学习因子和正交最小二乘是当前工作的主题。

著录项

  • 作者

    Tyagi, Kanishka.;

  • 作者单位

    The University of Texas at Arlington.;

  • 授予单位 The University of Texas at Arlington.;
  • 学科 Engineering Electronics and Electrical.;Artificial Intelligence.
  • 学位 M.S.
  • 年度 2011
  • 页码 94 p.
  • 总页数 94
  • 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