Can neural nets be universal approximators for fuzzy functions?

被引：17
|
作者：
Buckley, JJ [1 ]
Hayashi, Y
机构：
[1] Univ Alabama, Dept Math, Birmingham, AL 35294 USA
[2] Meiji Univ, Dept Comp Sci, Tama Ku, Kawasaki, Kanagawa 21471, Japan
来源：
FUZZY SETS AND SYSTEMS | 1999年 / 101卷 / 03期
关键词：
neural nets; fuzzy functions; interval arithmetic; universal approximator;
D O I：
10.1016/S0165-0114(97)00069-9
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
We first argue that the extension principle is too computationally involved to be an efficient way for a computer to evaluate fuzzy functions. We then suggest using a-cuts and interval arithmetic to compute the values of fuzzy functions. Using this method of computing fuzzy functions, we then show that neural nets are universal approximators for (computable) fuzzy functions, when we only input non-negative, or non-positive, fuzzy numbers. (C) 1999 Elsevier Science B.V. All rights reserved.
引用
收藏
页码：323 / 330
页数：8
相关论文
共 50 条
  • [41] Universal ε-approximators for integrals
    Langberg, Michael
    Schulman, Leonard J.
    [J]. PROCEEDINGS OF THE TWENTY-FIRST ANNUAL ACM-SIAM SYMPOSIUM ON DISCRETE ALGORITHMS, 2010, 135 : 598 - +
  • [42] ReLU Networks Are Universal Approximators via Piecewise Linear or Constant Functions
    Huang, Changcun
    [J]. NEURAL COMPUTATION, 2020, 32 (11) : 2249 - 2278
  • [43] Relu networks are universal approximators via piecewise linear or constant functions
    Huang, Changcun
    [J]. Neural Computation, 2020, 32 (11): : 2249 - 2278
  • [44] Neural nets and fuzzy logic
    Tinham, B
    [J]. CONTROL AND INSTRUMENTATION, 1996, 28 (06): : 41 - 42
  • [45] Fuzzy neural Petri nets
    Xu, Hua
    Wang, Yuan
    Jia, Peifa
    [J]. ADVANCES IN NEURAL NETWORKS - ISNN 2007, PT 2, PROCEEDINGS, 2007, 4492 : 328 - +
  • [46] Radial basis function neural networks of Hankel translates as universal approximators
    Marrero, Isabel
    [J]. ANALYSIS AND APPLICATIONS, 2019, 17 (06) : 897 - 930
  • [47] Neural nets/fuzzy logic
    Tinham, Brian
    [J]. Control and Instrumentation, 1996, 28 (06):
  • [48] The fuzzy rule-number estimation of T-S fuzzy models as universal approximators
    Liu, Fengqiu
    Xue, Xiaoping
    Wang, Jianmin
    [J]. FIFTH INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY, VOL 1, PROCEEDINGS, 2008, : 462 - +
  • [49] Universal approximation of a class of continuous fuzzy valued functions by regular fuzzy neural networks
    Liu, Puyin
    Wang, Huaxing
    [J]. Tien Tzu Hsueh Pao/Acta Electronica Sinica, 1997, 25 (11): : 41 - 45
  • [50] On the (1+1/2) layer neural networks as universal approximators
    Ciuca, I
    Ware, JA
    [J]. IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE, 1998, : 1218 - 1223
12345