Robustness of fuzzy flip-flop based neural networks

Rita Lovassy, L. Kóczy, László Gál

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

1 Citation (Scopus)

Abstract

In this paper the robustness of three different types of Fuzzy Flip-Flop based Neural Network (FNN) and the standard tansig based neural networks is compared from the various test function approximation goodness points of view. It is tested how well the fuzzy flip-flop based and the simulated neural networks handle the test data sets outlier points. The robust design of the FNN is presented, and the best suitable fuzzy neuron type is emphasized. Furthermore, the sensitivity of fuzzy neural networks to the fuzzy neuron type and hidden layers neuron number is evaluated.

Original languageEnglish
Title of host publication11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010 - Proceedings
Pages207-211
Number of pages5
DOIs
Publication statusPublished - 2010
Event11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010 - Budapest, Hungary
Duration: Nov 18 2010Nov 20 2010

Other

Other11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010
CountryHungary
CityBudapest
Period11/18/1011/20/10

Fingerprint

Flip flop circuits
Neurons
Neural networks
Fuzzy neural networks

ASJC Scopus subject areas

  • Artificial Intelligence
  • Information Systems

Cite this

Lovassy, R., Kóczy, L., & Gál, L. (2010). Robustness of fuzzy flip-flop based neural networks. In 11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010 - Proceedings (pp. 207-211). [5672248] https://doi.org/10.1109/CINTI.2010.5672248

Robustness of fuzzy flip-flop based neural networks. / Lovassy, Rita; Kóczy, L.; Gál, László.

11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010 - Proceedings. 2010. p. 207-211 5672248.

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

Lovassy, R, Kóczy, L & Gál, L 2010, Robustness of fuzzy flip-flop based neural networks. in 11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010 - Proceedings., 5672248, pp. 207-211, 11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010, Budapest, Hungary, 11/18/10. https://doi.org/10.1109/CINTI.2010.5672248
Lovassy R, Kóczy L, Gál L. Robustness of fuzzy flip-flop based neural networks. In 11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010 - Proceedings. 2010. p. 207-211. 5672248 https://doi.org/10.1109/CINTI.2010.5672248
Lovassy, Rita ; Kóczy, L. ; Gál, László. / Robustness of fuzzy flip-flop based neural networks. 11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010 - Proceedings. 2010. pp. 207-211
@inproceedings{30823cbd88d44deb979de7d85e58642e,
title = "Robustness of fuzzy flip-flop based neural networks",
abstract = "In this paper the robustness of three different types of Fuzzy Flip-Flop based Neural Network (FNN) and the standard tansig based neural networks is compared from the various test function approximation goodness points of view. It is tested how well the fuzzy flip-flop based and the simulated neural networks handle the test data sets outlier points. The robust design of the FNN is presented, and the best suitable fuzzy neuron type is emphasized. Furthermore, the sensitivity of fuzzy neural networks to the fuzzy neuron type and hidden layers neuron number is evaluated.",
author = "Rita Lovassy and L. K{\'o}czy and L{\'a}szl{\'o} G{\'a}l",
year = "2010",
doi = "10.1109/CINTI.2010.5672248",
language = "English",
isbn = "9781424492800",
pages = "207--211",
booktitle = "11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010 - Proceedings",

}

TY - GEN

T1 - Robustness of fuzzy flip-flop based neural networks

AU - Lovassy, Rita

AU - Kóczy, L.

AU - Gál, László

PY - 2010

Y1 - 2010

N2 - In this paper the robustness of three different types of Fuzzy Flip-Flop based Neural Network (FNN) and the standard tansig based neural networks is compared from the various test function approximation goodness points of view. It is tested how well the fuzzy flip-flop based and the simulated neural networks handle the test data sets outlier points. The robust design of the FNN is presented, and the best suitable fuzzy neuron type is emphasized. Furthermore, the sensitivity of fuzzy neural networks to the fuzzy neuron type and hidden layers neuron number is evaluated.

AB - In this paper the robustness of three different types of Fuzzy Flip-Flop based Neural Network (FNN) and the standard tansig based neural networks is compared from the various test function approximation goodness points of view. It is tested how well the fuzzy flip-flop based and the simulated neural networks handle the test data sets outlier points. The robust design of the FNN is presented, and the best suitable fuzzy neuron type is emphasized. Furthermore, the sensitivity of fuzzy neural networks to the fuzzy neuron type and hidden layers neuron number is evaluated.

UR - http://www.scopus.com/inward/record.url?scp=78651479469&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78651479469&partnerID=8YFLogxK

U2 - 10.1109/CINTI.2010.5672248

DO - 10.1109/CINTI.2010.5672248

M3 - Conference contribution

SN - 9781424492800

SP - 207

EP - 211

BT - 11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010 - Proceedings

ER -