Fuzzy Flip-Flop based Neural Networks as a novel implementation possibility of multilayer perceptrons

Rita Lovassy, László T. Kóczy, László Gál, Imre J. Rudas, Árpád Tóth

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

2 Citations (Scopus)

Abstract

Fuzzy Flip-Flop based Neural Networks (FNN) constructed from fuzzy D flip-flops are studied as a novel technique to implement multilayer perceptrons. The starting point of this approach is the concept of fuzzy flip-flop (F 3), as the extension of the binary counterpart. Fuzzy D flip-flop based neurons are viewed, as sigmoid function generators. Their characteristic equations contain simple fuzzy operations, thus enabling easy implementability. FNNs have an interconnected fuzzy neuron structure composed from a large number of neurons acting in parallel which are capable of learning, and are suitable for function approximation. In this paper we propose the FPGA implementation of ukasiewicz operations, furthermore of fuzzy D flip-flop neurons based on Łukasiewicz norms.

Original languageEnglish
Title of host publication2012 IEEE I2MTC - International Instrumentation and Measurement Technology Conference, Proceedings
Pages280-285
Number of pages6
DOIs
Publication statusPublished - Jul 30 2012
Event2012 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2012 - Graz, Austria
Duration: May 13 2012May 16 2012

Publication series

Name2012 IEEE I2MTC - International Instrumentation and Measurement Technology Conference, Proceedings

Other

Other2012 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2012
CountryAustria
CityGraz
Period5/13/125/16/12

Keywords

  • function approximation
  • fuzzy flip-flop
  • fuzzy neural network
  • hardware realization of ukasiewicz type fuzzy flip-flop neurons

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Fuzzy Flip-Flop based Neural Networks as a novel implementation possibility of multilayer perceptrons'. Together they form a unique fingerprint.

  • Cite this

    Lovassy, R., Kóczy, L. T., Gál, L., Rudas, I. J., & Tóth, Á. (2012). Fuzzy Flip-Flop based Neural Networks as a novel implementation possibility of multilayer perceptrons. In 2012 IEEE I2MTC - International Instrumentation and Measurement Technology Conference, Proceedings (pp. 280-285). [6229326] (2012 IEEE I2MTC - International Instrumentation and Measurement Technology Conference, Proceedings). https://doi.org/10.1109/I2MTC.2012.6229326