Approximation by radial bases and neural networks

被引：23

作者：

Li, X

Micchelli, CA

机构：

[1] Univ Nevada, Dept Math Sci, Las Vegas, NV 89154 USA

[2] SUNY Albany, Dept Math & Stat, Albany, NY 12222 USA

来源：

NUMERICAL ALGORITHMS | 2000年 / 25卷 / 1-4期

关键词：

approximation; radial basis functions; neural networks;

D O I：

10.1023/A:1016685729545

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

In this paper, we study approximation by radial basis functions including Gaussian, multiquadric, and thin plate spline functions, and derive order of approximation under certain conditions. Moreover, neural networks are also constructed by wavelet recovery formula and wavelet frames.

引用

页码：241 / 262

页数：22

共 16 条

[1]

ANASTASSIOU G, IN PRESS COMPUT MATH

[2] Rate of convergence of some neural network operators to the unit-univariate case [J].