Constructive Approximation of Discontinuous Functions by Neural Networks

被引：0
|
作者：
B. Llanas
S. Lantarón
F. J. Sáinz
机构：
[1] Universidad Politécnica de Madrid,Departamento de Matemática Aplicada, E.T.S.I. de Caminos
来源：
Neural Processing Letters | 2008年 / 27卷
关键词：
Approximation of discontinuous functions; Constructive approximation; Piecewise continuous functions; Neural networks; Gibbs phenomenon;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
In this paper, we give a constructive proof that a real, piecewise continuous function can be almost uniformly approximated by single hidden-layer feedforward neural networks (SLFNNs). The construction procedure avoids the Gibbs phenomenon. Computer experiments show that the resulting approximant is much more accurate than SLFNNs trained by gradient descent.
引用
收藏
页码：209 / 226
页数：17
相关论文
共 50 条
  • [1] Constructive approximation of discontinuous functions by neural networks
    Llanas, B.
    Lantaron, S.
    Sainz, F. J.
    [J]. NEURAL PROCESSING LETTERS, 2008, 27 (03) : 209 - 226
  • [2] Constructive function approximation by neural networks with optimized activation functions and fixed weights
    Li, Feng-Jun
    [J]. NEURAL COMPUTING & APPLICATIONS, 2019, 31 (09): : 4613 - 4628
  • [3] Constructive function approximation by neural networks with optimized activation functions and fixed weights
    Feng-Jun Li
    [J]. Neural Computing and Applications, 2019, 31 : 4613 - 4628
  • [4] Statistical approximation learning of discontinuous functions using simultaneous recurrent neural networks
    Sakai, M
    Homma, N
    Gupta, MI
    Abe, K
    [J]. PROCEEDINGS OF THE 2002 IEEE INTERNATIONAL SYMPOSIUM ON INTELLIGENT CONTROL, 2002, : 434 - 439
  • [5] CONSTRUCTIVE ESTIMATION OF APPROXIMATION FOR TRIGONOMETRIC NEURAL NETWORKS
    Wang, Jianjun
    Xu, Weihua
    Zou, Bin
    [J]. INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING, 2012, 10 (03)
  • [6] Constructive Approximation Method of Polynomial by Neural Networks
    Wang, Jianjun
    Xu, Zongben
    Jing, Jia
    [J]. ADVANCES IN COGNITIVE NEURODYNAMICS, PROCEEDINGS, 2008, : 1033 - +
  • [7] Approximation of discontinuous inverse operators with neural networks
    Massa, Paolo
    Garbarino, Sara
    Benvenuto, Federico
    [J]. INVERSE PROBLEMS, 2022, 38 (10)
  • [8] CONSTRUCTIVE APPROXIMATIONS FOR NEURAL NETWORKS BY SIGMOIDAL FUNCTIONS
    JONES, LK
    [J]. PROCEEDINGS OF THE IEEE, 1990, 78 (10) : 1586 - 1589
  • [9] Constructive approximation to real function by wavelet neural networks
    Hou Muzhou
    Han Xuli
    Gan Yixuan
    [J]. Neural Computing and Applications, 2009, 18 : 883 - 889
  • [10] CONSTRUCTIVE APPROXIMATION BY NEURAL NETWORKS WITH POSITIVE INTEGER WEIGHTS
    Hong, Bum Il
    Hahm, Nahmwoo
    [J]. KOREAN JOURNAL OF MATHEMATICS, 2015, 23 (03): : 327 - 336
12345