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
  • [21] CONSTRUCTIVE NEURAL NETWORKS AS ESTIMATORS OF BAYESIAN DISCRIMINANT FUNCTIONS
    YEUNG, DY
    PATTERN RECOGNITION, 1993, 26 (01) : 189 - 204
  • [22] Neural networks for approximation of real functions with the Gaussian functions
    Han, Xuli
    Hou, Muzhou
    ICNC 2007: THIRD INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, VOL 1, PROCEEDINGS, 2007, : 601 - +
  • [23] On Multistability of Competitive Neural Networks with Discontinuous Activation Functions
    Nie, Xiaobing
    Zheng, Wei Xing
    2014 4TH AUSTRALIAN CONTROL CONFERENCE (AUCC), 2014, : 245 - 250
  • [24] Approximating functions by neural networks: A constructive solution in the uniform norm
    Meltser, M
    Shoham, M
    Manevitz, LM
    NEURAL NETWORKS, 1996, 9 (06) : 965 - 978
  • [25] On the approximation of rough functions with deep neural networks
    De Ryck T.
    Mishra S.
    Ray D.
    SeMA Journal, 2022, 79 (3) : 399 - 440
  • [26] Approximation of compositional functions with ReLU neural networks
    Gong, Qi
    Kang, Wei
    Fahroo, Fariba
    SYSTEMS & CONTROL LETTERS, 2023, 175
  • [27] APPROXIMATION BY SPHERICAL NEURAL NETWORKS WITH ZONAL FUNCTIONS
    Chen, Zhixiang
    Cao, Feilong
    ANZIAM JOURNAL, 2017, 58 (3-4): : 238 - 246
  • [28] Approximation by Spherical Neural Networks with Sigmoidal Functions
    Cao, Feilong
    Chen, Zhixiang
    JOURNAL OF COMPUTATIONAL ANALYSIS AND APPLICATIONS, 2015, 18 (02) : 390 - 396
  • [29] Constructive Approximation by Superposition of Sigmoidal Functions
    Danilo Costarelli
    Renato Spigler
    Analysis in Theory and Applications, 2013, 29 (02) : 169 - 196
  • [30] Synchronization of Interconnected Discontinuous Neural Networks With Nonlinear Coupling Functions
    Wang, Zengyun
    Liu, Xinzhi
    IEEE ACCESS, 2019, 7 : 25804 - 25814
12345