Function approximation performance of Fuzzy Neural Networks based on frequently used fuzzy operations and a pair of new trigonometric norms

László Gál, Rita Lovassy, L. Kóczy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

A new triangular t-norm and t-conorm are presented. The new fuzzy operations combined with the standard negation are applied in a practical problem, namely, they are proposed as suitable triangular norms for defining a fuzzy flip-flop based neuron. Other fuzzy J-K and D flip-flop based neurons are constructed by using algebraic, Lukasiewicz, Yager, Dombi and Hamacher connectives. The function approximation performance of a Fuzzy Neural Networks (FNN) built up from various fuzzy neurons are evaluated using six increasingly more complicated problems: various sine waves, battery cell charging characteristics, two dimensional trigonometric functions and a six dimensional benchmark problem. It is shown that the new norms lead to FNNs with better approximation properties in some cases than all the previous ones.

Original languageEnglish
Title of host publication2010 IEEE World Congress on Computational Intelligence, WCCI 2010
DOIs
Publication statusPublished - 2010
Event2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - Barcelona, Spain
Duration: Jul 18 2010Jul 23 2010

Other

Other2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010
CountrySpain
CityBarcelona
Period7/18/107/23/10

Fingerprint

Fuzzy neural networks
Neurons
Flip flop circuits

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics

Cite this

Function approximation performance of Fuzzy Neural Networks based on frequently used fuzzy operations and a pair of new trigonometric norms. / Gál, László; Lovassy, Rita; Kóczy, L.

2010 IEEE World Congress on Computational Intelligence, WCCI 2010. 2010. 5584252.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Gál, L, Lovassy, R & Kóczy, L 2010, Function approximation performance of Fuzzy Neural Networks based on frequently used fuzzy operations and a pair of new trigonometric norms. in 2010 IEEE World Congress on Computational Intelligence, WCCI 2010., 5584252, 2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010, Barcelona, Spain, 7/18/10. https://doi.org/10.1109/FUZZY.2010.5584252
Gál, László ; Lovassy, Rita ; Kóczy, L. / Function approximation performance of Fuzzy Neural Networks based on frequently used fuzzy operations and a pair of new trigonometric norms. 2010 IEEE World Congress on Computational Intelligence, WCCI 2010. 2010.
@inproceedings{3f332003fdba4017b97c498b58d0a31a,
title = "Function approximation performance of Fuzzy Neural Networks based on frequently used fuzzy operations and a pair of new trigonometric norms",
abstract = "A new triangular t-norm and t-conorm are presented. The new fuzzy operations combined with the standard negation are applied in a practical problem, namely, they are proposed as suitable triangular norms for defining a fuzzy flip-flop based neuron. Other fuzzy J-K and D flip-flop based neurons are constructed by using algebraic, Lukasiewicz, Yager, Dombi and Hamacher connectives. The function approximation performance of a Fuzzy Neural Networks (FNN) built up from various fuzzy neurons are evaluated using six increasingly more complicated problems: various sine waves, battery cell charging characteristics, two dimensional trigonometric functions and a six dimensional benchmark problem. It is shown that the new norms lead to FNNs with better approximation properties in some cases than all the previous ones.",
author = "L{\'a}szl{\'o} G{\'a}l and Rita Lovassy and L. K{\'o}czy",
year = "2010",
doi = "10.1109/FUZZY.2010.5584252",
language = "English",
isbn = "9781424469208",
booktitle = "2010 IEEE World Congress on Computational Intelligence, WCCI 2010",

}

TY - GEN

T1 - Function approximation performance of Fuzzy Neural Networks based on frequently used fuzzy operations and a pair of new trigonometric norms

AU - Gál, László

AU - Lovassy, Rita

AU - Kóczy, L.

PY - 2010

Y1 - 2010

N2 - A new triangular t-norm and t-conorm are presented. The new fuzzy operations combined with the standard negation are applied in a practical problem, namely, they are proposed as suitable triangular norms for defining a fuzzy flip-flop based neuron. Other fuzzy J-K and D flip-flop based neurons are constructed by using algebraic, Lukasiewicz, Yager, Dombi and Hamacher connectives. The function approximation performance of a Fuzzy Neural Networks (FNN) built up from various fuzzy neurons are evaluated using six increasingly more complicated problems: various sine waves, battery cell charging characteristics, two dimensional trigonometric functions and a six dimensional benchmark problem. It is shown that the new norms lead to FNNs with better approximation properties in some cases than all the previous ones.

AB - A new triangular t-norm and t-conorm are presented. The new fuzzy operations combined with the standard negation are applied in a practical problem, namely, they are proposed as suitable triangular norms for defining a fuzzy flip-flop based neuron. Other fuzzy J-K and D flip-flop based neurons are constructed by using algebraic, Lukasiewicz, Yager, Dombi and Hamacher connectives. The function approximation performance of a Fuzzy Neural Networks (FNN) built up from various fuzzy neurons are evaluated using six increasingly more complicated problems: various sine waves, battery cell charging characteristics, two dimensional trigonometric functions and a six dimensional benchmark problem. It is shown that the new norms lead to FNNs with better approximation properties in some cases than all the previous ones.

UR - http://www.scopus.com/inward/record.url?scp=78549250371&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78549250371&partnerID=8YFLogxK

U2 - 10.1109/FUZZY.2010.5584252

DO - 10.1109/FUZZY.2010.5584252

M3 - Conference contribution

SN - 9781424469208

BT - 2010 IEEE World Congress on Computational Intelligence, WCCI 2010

ER -