首页> 外文会议>IEEE International Conference on Neural Networks >An /spl epsi/-approximation approach for global optimization with an application to neural networks
【24h】

An /spl epsi/-approximation approach for global optimization with an application to neural networks

机译:AN / SPL EPSI / - 具有神经网络应用程序的全局优化的批视方法

获取原文

摘要

This paper proposes an /spl epsi/-approximation approach based on the tunneling methods for finding a globally optimal solution of a function of several variables. In this approach, after some locally minimal solution is found, one must obtain a new initial point from which a better local solution can be obtained by a gradient method. For that, a Newton-like method called the restoration procedure is used. Computational results of several standard test problems are presented. Further more, an application to hierarchical neural networks is discussed. Global optimization is an unavoidable task for optimizing a neural network, since a hierarchical neural network with repeated nonlinear mapping has generally many local minima with respect to weighting coefficients.
机译:本文提出了一种基于隧道方法的AN / SPL EPSI / - 克约方法,用于查找若干变量函数的全局最佳解决方案。在这种方法中,在找到一些局部最小的解决方案之后,必须获得新的初始点,从中可以通过梯度方法获得更好的局部解决方案。为此,使用称为恢复过程的牛顿样方法。提出了几个标准测试问题的计算结果。此外,讨论了对分层神经网络的应用。全局优化是用于优化神经网络的不可避免的任务,因为具有重复非线性映射的分层神经网络通常是关于加权系数的许多局部最小值。

著录项

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