zbMATH — the first resource for mathematics

Geometry Search for the term Geometry in any field. Queries are case-independent.
Funct* Wildcard queries are specified by * (e.g. functions, functorial, etc.). Otherwise the search is exact.
"Topological group" Phrases (multi-words) should be set in "straight quotation marks".
au: Bourbaki & ti: Algebra Search for author and title. The and-operator & is default and can be omitted.
Chebyshev | Tschebyscheff The or-operator | allows to search for Chebyshev or Tschebyscheff.
"Quasi* map*" py: 1989 The resulting documents have publication year 1989.
so: Eur* J* Mat* Soc* cc: 14 Search for publications in a particular source with a Mathematics Subject Classification code (cc) in 14.
"Partial diff* eq*" ! elliptic The not-operator ! eliminates all results containing the word elliptic.
dt: b & au: Hilbert The document type is set to books; alternatively: j for journal articles, a for book articles.
py: 2000-2015 cc: (94A | 11T) Number ranges are accepted. Terms can be grouped within (parentheses).
la: chinese Find documents in a given language. ISO 639-1 language codes can also be used.

a & b logic and
a | b logic or
!ab logic not
abc* right wildcard
"ab c" phrase
(ab c) parentheses
any anywhere an internal document identifier
au author, editor ai internal author identifier
ti title la language
so source ab review, abstract
py publication year rv reviewer
cc MSC code ut uncontrolled term
dt document type (j: journal article; b: book; a: book article)
Approximation of fuzzy functions by regular fuzzy neural networks. (English) Zbl 1242.41019
Summary: We investigate the ability of regular fuzzy neural networks to provide approximations to fuzzy functions. Since the operation of regular fuzzy neural networks is based on Zadeh’s extension principle, we first present a level characterization of the Zadeh’s extensions of level-continuous fuzzy-valued functions and consider the continuity of these extensions. On the basis of this, we give characterizations of fuzzy functions which can be approximated by a class of four-layer regular fuzzy neural networks according to supremum-metric and level convergence.

41A30Approximation by other special function classes
68T05Learning and adaptive systems
26E50Fuzzy real analysis
Full Text: DOI
[1] L.C. Barros, R.C. Bassanezi, P.A. Tonelli, On the continuity of the Zadeh’s extension, in: Proceedings of the IFSA’97 Congress, Prague, 1997.
[2] Buckley, J. J.; Hayashi, Y.: Can fuzzy neural nets approximate continuous fuzzy functions, Fuzzy sets and systems 61, 43-51 (1994) · Zbl 0837.68088 · doi:10.1016/0165-0114(94)90283-6
[3] Diamond, P.; Kloeden, P.: Metric space of fuzzy sets --- theory and application, (1994) · Zbl 0873.54019
[4] Dubois, D.; Kerre, E.; Mesiar, R.; Prade, H.: Fuzzy interval analysis, Fundamentals of fuzzy sets, the handbooks of fuzzy sets series, 483-581 (2000) · Zbl 0988.26020
[5] Fang, J.; Huang, H.: Some properties of the level convergence topology on fuzzy number space en, Fuzzy sets and systems 140, 509-517 (2003) · Zbl 1052.54007 · doi:10.1016/S0165-0114(02)00576-6
[6] Fang, J.; Huang, H.: On the level convergence of a sequence of fuzzy numbers, Fuzzy sets and systems 147, 417-435 (2004) · Zbl 1053.26020 · doi:10.1016/j.fss.2003.08.001
[7] Goetschel, R.; Voxman, W.: Elementary calculus, Fuzzy sets and systems 18, No. 1, 31-43 (1986) · Zbl 0626.26014 · doi:10.1016/0165-0114(86)90026-6
[8] Hornik, K.: Approximation capabilities of multilayer feedforward networks, Neural networks 4, 251-257 (1991)
[9] Huang, H.; Wu, C.: Approximation of level continuous fuzzy-valued functions by multilayer regular fuzzy neural networks, Mathematical and computer modelling 49, 1311-1318 (2009) · Zbl 1165.41313 · doi:10.1016/j.mcm.2008.12.013
[10] Huang, H.; Wu, C.: Approximation capabilities of multilayer fuzzy neural networks on the set of fuzzy-valued functions, Information sciences 179, 2762-2773 (2009) · Zbl 1192.68521 · doi:10.1016/j.ins.2009.04.004
[11] Huang, H.: Some notes on zadeh’s extensions, Information sciences 180, 3806-3813 (2010) · Zbl 1202.03058 · doi:10.1016/j.ins.2010.05.023
[12] Ishibuchi, H.; Nii, M.: Numerical analysis of the learning of fuzzified neural networks from fuzzy if -- then rules, Fuzzy sets and systems 120, 281-307 (2001) · Zbl 1013.68177 · doi:10.1016/S0165-0114(99)00070-6
[13] Kelly, J. L.: General topology, (1975) · Zbl 0307.46044
[14] Liu, P.; Wang, H.: Approximation capability of regular fuzzy neural networks to continuous fuzzy functions, Science in China (Series E) 42, 175-182 (1999) · Zbl 0946.68122 · doi:10.1007/BF02917113
[15] Liu, P.: Analyses of regular fuzzy neural networks for approximation capabilities, Fuzzy sets and systems 114, 329-338 (2000) · Zbl 0966.93064 · doi:10.1016/S0165-0114(98)00248-6
[16] Liu, P.: Universal approximations of continuous fuzzy-valued function by multi-layer regular fuzzy neural networks, Fuzzy sets and systems 119, 313-320 (2001) · Zbl 0976.93055 · doi:10.1016/S0165-0114(99)00132-3
[17] Liu, P.; Li, H.: Approximation analysis of feedforward regular fuzzy neural network with two hidden layers, Fuzzy sets and systems 150, 373-396 (2005) · Zbl 1087.41018 · doi:10.1016/j.fss.2004.02.013
[18] Negoita, C.; Ralescu, D.: Application of fuzzy sets to system analysis, (1975) · Zbl 0326.94002
[19] Nguyen, H. T.: A note on the extension principle for fuzzy sets, Journal of mathematical analysis and applications 64, 369-380 (1978) · Zbl 0377.04004 · doi:10.1016/0022-247X(78)90045-8
[20] Román-Flores, H.; Barros, L. C.; Bassanezi, R. C.: A note on zadeh’s extensions, Fuzzy sets and systems 117, 327-331 (2001) · Zbl 0968.54007 · doi:10.1016/S0165-0114(98)00408-4
[21] Scarselli, F.; Tsoi, A. C.: Universal approximation using feedforward neural networks: a survey of some existing methods, and some new results, Neural networks 11, No. 1, 15-37 (1998)
[22] Wu, C.; Ma, M.: The basic of fuzzy analysis (in chinese), (1991)
[23] Zadeh, L.: The concept of a linguistic variable and its application to approximate reasoning, Information science 8, 199-249 (1975) · Zbl 0397.68071