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

页码：323 / 330

页数：8

共 50 条

[31] Fuzzy continuous input-output controllers are universal approximators
Wang, GJ
[J]. FUZZY SETS AND SYSTEMS, 1998, 97 (01) : 95 - 99
[32] Fuzzy continuous input-output controllers are universal approximators
[J]. Fuzzy Sets Syst, 1 (95-99):
[33] Necessary conditions for general MISO fuzzy systems as universal approximators
Ding, YS
Ying, H
Shao, SH
[J]. SMC '97 CONFERENCE PROCEEDINGS - 1997 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS, VOLS 1-5: CONFERENCE THEME: COMPUTATIONAL CYBERNETICS AND SIMULATION, 1997, : 3176 - 3181
[34] g-normal fuzzy relational models are universal approximators
Raja, Pandora
Aghili-Ashtiani, Arya
[J]. FUZZY SETS AND SYSTEMS, 2023, 471
[35] Fuzzy systems are universal approximators for a smooth function and its derivatives
Kreinovich, V
Nguyen, HT
Yam, Y
[J]. INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, 2000, 15 (06) : 565 - 574
[36] Necessary conditions for some typical fuzzy systems as universal approximators
Ying, H
Chen, GR
[J]. AUTOMATICA, 1997, 33 (07) : 1333 - 1338
[37] General Takagi-Sugeno fuzzy systems are universal approximators
Ying, H
[J]. 1998 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AT THE IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE - PROCEEDINGS, VOL 1-2, 1998, : 819 - 823
[38] Multilayer perceptrons and radial basis functions are universal robust approximators
Lo, JTH
[J]. IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE, 1998, : 1311 - 1314
[39] Neural networks with a continuous squashing function in the output are universal approximators
Castro, JL
Mantes, CJ
Benítez, JM
[J]. NEURAL NETWORKS, 2000, 13 (06) : 561 - 563
[40] Universal approximation of fuzzy functions by polygonal fuzzy neural networks with general inputs
He, Chun-Mei
Ye, You-Pei
Li, Jian
Xu, Wei-Hong
[J]. Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence, 2009, 22 (03): : 481 - 487

← 1 2 3 4 5 →