首页> 外文会议>International Symposium on Intelligence Computation amp; Applications(ISICA'2007); 20070921-23; Wuhan(CN) >Approximate Interpolation by Neural Networks with the Inverse Multiquadric Functions
【24h】

Approximate Interpolation by Neural Networks with the Inverse Multiquadric Functions

机译:具有逆多二次函数的神经网络的近似插值

获取原文
获取原文并翻译 | 示例

摘要

For approximate interpolation, a type of single-hidden layer feedforward neural networks with the inverse multiquadric activation function is presented in this paper. We give a new and quantitative proof of the fact that a single layer neural networks with n +1 hidden neurons can learn n + 1 distinct samples with zero error. Based on this result, approximate interpolants are given. They can approximate interpolate, with arbitrary precision, any set of distinct data in one or several dimensions. They can uniformly approximate any C~1 continuous function of one variable.
机译:对于近似插值,本文提出了一种具有逆多二次激活函数的单隐层前馈神经网络。我们提供了一个新的定量证据,证明具有n +1个隐藏神经元的单层神经网络可以学习n + 1个零误差的样本。基于此结果,给出了近似的内插值。它们可以任意精度近似地对一个或多个维度上的任意一组不同数据进行插值。它们可以统一逼近一个变量的任何C〜1连续函数。

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