Conditions for Radial Basis Function Neural networks to Universal Approximation and Numerical Experiments

被引：0
|
作者：
Nong, Jifu [1 ]
机构：
[1] Guangxi Univ Nationalities, Coll Sci, Nanning 530006, Peoples R China
来源：
2013 25TH CHINESE CONTROL AND DECISION CONFERENCE (CCDC) | 2013年
关键词：
Universal Approximation; Radial Basis Function networks; Numerical Experiments;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this paper, we investigate the universal approximation property of Radial Basis Function (RBF) networks. We show that RBFs are not required to be integrable for the REF networks to be universal approximators. Instead, RBF networks can uniformly approximate any continuous function on a compact set provided that the radial basis activation function is continuous almost everywhere, locally essentially bounded, and not a polynomial. The approximation is also discussed. Some experimental results are reported to illustrate our findings.
引用
收藏
页码：2193 / 2197
页数：5
相关论文
共 50 条
  • [21] A sigmoidal radial basis function neural network for function approximation
    Tsai, JR
    Chung, PC
    Chang, CI
    [J]. ICNN - 1996 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS. 1-4, 1996, : 496 - 501
  • [22] Comparative study between radial basis probabilistic neural networks and radial basis function neural networks
    Zhao, WB
    Huang, DS
    Guo, L
    [J]. INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING, 2003, 2690 : 389 - 396
  • [23] Universal approximation with neural networks on function spaces
    Kumagai, Wataru
    Sannai, Akiyoshi
    Kawano, Makoto
    [J]. JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE, 2024, 36 (07) : 1089 - 1100
  • [24] Comparison of function approximation with sigmoid and radial basis function networks
    Russell, G
    Fausett, LV
    [J]. APPLICATIONS AND SCIENCE OF ARTIFICIAL NEURAL NETWORKS II, 1996, 2760 : 61 - 72
  • [25] Choice of the radial basis function approximation in neural networks used for fuzzy system implementation
    Reznik, L
    Little, A
    [J]. JOINT 9TH IFSA WORLD CONGRESS AND 20TH NAFIPS INTERNATIONAL CONFERENCE, PROCEEDINGS, VOLS. 1-5, 2001, : 3032 - 3037
  • [26] Cosine radial basis function neural networks
    Randolph-Gips, MM
    Karayiannis, NB
    [J]. PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS 2003, VOLS 1-4, 2003, : 96 - 101
  • [27] Robust radial basis function neural networks
    Lee, CC
    Chung, PC
    Tsai, JR
    Chang, CI
    [J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 1999, 29 (06): : 674 - 685
  • [28] Monotonicity conditions for radial basis function networks
    Husek, Petr
    [J]. 2018 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI), 2018, : 168 - 173
  • [29] Approximation with direction basis function neural networks
    Cao, WM
    Feng, H
    Wang, SJ
    [J]. 2002 IEEE REGION 10 CONFERENCE ON COMPUTERS, COMMUNICATIONS, CONTROL AND POWER ENGINEERING, VOLS I-III, PROCEEDINGS, 2002, : 1290 - 1293
  • [30] Annealing robust radial basis function networks for function approximation with outliers
    Chuang, CC
    Jeng, JT
    Lin, PT
    [J]. NEUROCOMPUTING, 2004, 56 : 123 - 139
12345