Training neural networks with noisy data as an ill-posed problem

被引:0
|
作者
Martin Burger
Heinz W. Engl
机构
[1] Johannes Kepler Universität Linz,Industrial Mathematics Institute
来源
关键词
ill-posed problems; least-squares collocation; neural networks; network training; regularization;
D O I
暂无
中图分类号
学科分类号
摘要
This paper is devoted to the analysis of network approximation in the framework of approximation and regularization theory. It is shown that training neural networks and similar network approximation techniques are equivalent to least-squares collocation for a corresponding integral equation with mollified data.
引用
收藏
页码:335 / 354
页数:19
相关论文
共 50 条