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
  • [41] ASYMPTOTIC REGULARIZATION OF AN ILL-POSED IDENTIFICATION PROBLEM
    ISLAMOV, IM
    USSR COMPUTATIONAL MATHEMATICS AND MATHEMATICAL PHYSICS, 1988, 28 (03): : 129 - 136
  • [42] AN ILL-POSED PROBLEM FOR THE HEAT-EQUATION
    HAO, DN
    GORENFLO, R
    ZEITSCHRIFT FUR ANGEWANDTE MATHEMATIK UND MECHANIK, 1991, 71 (06): : T759 - T762
  • [43] On a new notion of the solution to an ill-posed problem
    Ramm, A. G.
    JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS, 2010, 234 (12) : 3326 - 3331
  • [44] A meshless method to the solution of an ill-posed problem
    Rostamian, Malihe
    Shahrezaee, Alimardan
    JOURNAL OF INVERSE AND ILL-POSED PROBLEMS, 2016, 24 (05): : 583 - 597
  • [45] Complexity and the problem of ill-posed questions in ecology
    Loehle, Craig
    ECOLOGICAL COMPLEXITY, 2011, 8 (01) : 60 - 67
  • [46] The generalized solution of ill-posed boundary problem
    CAO Weiping & MA Jipu Department of Mathematics and Physics
    Y. Y. Tseng Functional Analysis Research Centre
    ScienceinChina(SeriesA:Mathematics), 2006, (07) : 902 - 911
  • [47] The generalized solution of ill-posed boundary problem
    Cao Weiping
    Ma Jipu
    SCIENCE IN CHINA SERIES A-MATHEMATICS, 2006, 49 (07): : 902 - 911
  • [48] Solving ill-posed inverse problems using iterative deep neural networks
    Adler, Jonas
    Oktem, Ozan
    INVERSE PROBLEMS, 2017, 33 (12)
  • [49] Training Neural Networks on Noisy Data
    Rusiecki, Andrzej
    Kordos, Miroslaw
    Kaminski, Tomasz
    Gren, Krzysztof
    ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING ICAISC 2014, PT I, 2014, 8467 : 131 - 142
  • [50] A Well-Posed Logarithmic Counterpart of an Ill-Posed Cauchy Problem
    Lucas A. Santos
    Flank D. M. Bezerra
    Bulletin of the Brazilian Mathematical Society, New Series, 2023, 54