Fuzzy flip-flop based neural network as a function approximator

Rita Lovassy, László T. Kóczy, László Gál

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

2 Citations (Scopus)

Abstract

Artificial neural networks and fuzzy logic systems, in the context of approximate reasoning, share common features and techniques. A family of fuzzy flip-flops is proposed, based on an artificial neural network-like structure which is suitable for approximating many-input one-output nonlinear functions. The neurons in the multilayer perceptron networks typically employ sigmoidal activation functions. The next state of the fuzzy J-K flip-flops (F3) using Yager and Dombi operators present quasi-S-shaped characteristics. The paper proposes the investigation of the possibility of constructing multilayer perceptrons from such fuzzy units. Each of the two candidates for F 3-based neurons is examined for its training capability by evaluating and comparing the approximation properties in the context of different transcendental functions with one-input and multi-input cases. Simulation results are presented.

Original languageEnglish
Title of host publicationCIMSA 2008 - IEEE Conference on Computational Intelligence for Measurement Systems and Applications Proceedings
Pages44-49
Number of pages6
DOIs
Publication statusPublished - Sep 26 2008
Event2008 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, IEEE CIMSA 2008 - Istanbul, Turkey
Duration: Jul 14 2008Jul 16 2008

Publication series

NameCIMSA 2008 - IEEE Conference on Computational Intelligence for Measurement Systems and Applications Proceedings

Other

Other2008 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, IEEE CIMSA 2008
CountryTurkey
CityIstanbul
Period7/14/087/16/08

Keywords

  • Function approximation
  • Fuzzy flip-flop based neural network
  • J-K fuzzy flip-flop
  • Learning systems

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Control and Systems Engineering

Fingerprint Dive into the research topics of 'Fuzzy flip-flop based neural network as a function approximator'. Together they form a unique fingerprint.

  • Cite this

    Lovassy, R., Kóczy, L. T., & Gál, L. (2008). Fuzzy flip-flop based neural network as a function approximator. In CIMSA 2008 - IEEE Conference on Computational Intelligence for Measurement Systems and Applications Proceedings (pp. 44-49). [4595830] (CIMSA 2008 - IEEE Conference on Computational Intelligence for Measurement Systems and Applications Proceedings). https://doi.org/10.1109/CIMSA.2008.4595830