Multilayer perceptron implemented by fuzzy flip-flops

Rita Lovassy, L. Kóczy, László Gál

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

7 Citations (Scopus)

Abstract

The paper introduces a novel method for constructing Multilayer Perceptron (MLP) Neural Networks (NN) with the aid of fuzzy systems, particularly by deploying fuzzy J-K flip-flops as neurons. The next state Q(t+1) of the J-K fuzzy flip-flops (F3) in terms of input J can be characterized by a more or less S-shaped function, for each F3 derived from the Yager, Dombi, and Fodor norms and co-norms. In this approach, J represents the neuron input. The other input K is wired to the complemental output (K=1-Q), thus an elementary fuzzy sequential unit with a single input and a single output is received. The algebraic F3 having linear J-Q(t+1) characteristics is added to the above three. The paper proposes the investigation of the possibility of constructing multilayer perceptrons from such real fuzzy hardware units. Each of the four candidates for F3-based neurons is examined for its training capability by evaluating and comparing the approximation capabilities for two different transcendental functions. Simulation results are presented.

Original languageEnglish
Title of host publicationIEEE International Conference on Fuzzy Systems
Pages1683-1688
Number of pages6
DOIs
Publication statusPublished - 2008
Event2008 IEEE International Conference on Fuzzy Systems, FUZZ 2008 - Hong Kong, China
Duration: Jun 1 2008Jun 6 2008

Other

Other2008 IEEE International Conference on Fuzzy Systems, FUZZ 2008
CountryChina
CityHong Kong
Period6/1/086/6/08

Fingerprint

Flip flop circuits
Multilayer neural networks
Flip
Perceptron
Neurons
Multilayer
Neuron
Fuzzy systems
Norm
Transcendental function
Unit
Output
Fuzzy Systems
Neural networks
Hardware
Neural Networks
Approximation
Simulation

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Applied Mathematics
  • Theoretical Computer Science

Cite this

Lovassy, R., Kóczy, L., & Gál, L. (2008). Multilayer perceptron implemented by fuzzy flip-flops. In IEEE International Conference on Fuzzy Systems (pp. 1683-1688). [4630597] https://doi.org/10.1109/FUZZY.2008.4630597

Multilayer perceptron implemented by fuzzy flip-flops. / Lovassy, Rita; Kóczy, L.; Gál, László.

IEEE International Conference on Fuzzy Systems. 2008. p. 1683-1688 4630597.

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

Lovassy, R, Kóczy, L & Gál, L 2008, Multilayer perceptron implemented by fuzzy flip-flops. in IEEE International Conference on Fuzzy Systems., 4630597, pp. 1683-1688, 2008 IEEE International Conference on Fuzzy Systems, FUZZ 2008, Hong Kong, China, 6/1/08. https://doi.org/10.1109/FUZZY.2008.4630597
Lovassy R, Kóczy L, Gál L. Multilayer perceptron implemented by fuzzy flip-flops. In IEEE International Conference on Fuzzy Systems. 2008. p. 1683-1688. 4630597 https://doi.org/10.1109/FUZZY.2008.4630597
Lovassy, Rita ; Kóczy, L. ; Gál, László. / Multilayer perceptron implemented by fuzzy flip-flops. IEEE International Conference on Fuzzy Systems. 2008. pp. 1683-1688
@inproceedings{aa40d2a9da9a40a1901f4459cd92a846,
title = "Multilayer perceptron implemented by fuzzy flip-flops",
abstract = "The paper introduces a novel method for constructing Multilayer Perceptron (MLP) Neural Networks (NN) with the aid of fuzzy systems, particularly by deploying fuzzy J-K flip-flops as neurons. The next state Q(t+1) of the J-K fuzzy flip-flops (F3) in terms of input J can be characterized by a more or less S-shaped function, for each F3 derived from the Yager, Dombi, and Fodor norms and co-norms. In this approach, J represents the neuron input. The other input K is wired to the complemental output (K=1-Q), thus an elementary fuzzy sequential unit with a single input and a single output is received. The algebraic F3 having linear J-Q(t+1) characteristics is added to the above three. The paper proposes the investigation of the possibility of constructing multilayer perceptrons from such real fuzzy hardware units. Each of the four candidates for F3-based neurons is examined for its training capability by evaluating and comparing the approximation capabilities for two different transcendental functions. Simulation results are presented.",
author = "Rita Lovassy and L. K{\'o}czy and L{\'a}szl{\'o} G{\'a}l",
year = "2008",
doi = "10.1109/FUZZY.2008.4630597",
language = "English",
isbn = "9781424418190",
pages = "1683--1688",
booktitle = "IEEE International Conference on Fuzzy Systems",

}

TY - GEN

T1 - Multilayer perceptron implemented by fuzzy flip-flops

AU - Lovassy, Rita

AU - Kóczy, L.

AU - Gál, László

PY - 2008

Y1 - 2008

N2 - The paper introduces a novel method for constructing Multilayer Perceptron (MLP) Neural Networks (NN) with the aid of fuzzy systems, particularly by deploying fuzzy J-K flip-flops as neurons. The next state Q(t+1) of the J-K fuzzy flip-flops (F3) in terms of input J can be characterized by a more or less S-shaped function, for each F3 derived from the Yager, Dombi, and Fodor norms and co-norms. In this approach, J represents the neuron input. The other input K is wired to the complemental output (K=1-Q), thus an elementary fuzzy sequential unit with a single input and a single output is received. The algebraic F3 having linear J-Q(t+1) characteristics is added to the above three. The paper proposes the investigation of the possibility of constructing multilayer perceptrons from such real fuzzy hardware units. Each of the four candidates for F3-based neurons is examined for its training capability by evaluating and comparing the approximation capabilities for two different transcendental functions. Simulation results are presented.

AB - The paper introduces a novel method for constructing Multilayer Perceptron (MLP) Neural Networks (NN) with the aid of fuzzy systems, particularly by deploying fuzzy J-K flip-flops as neurons. The next state Q(t+1) of the J-K fuzzy flip-flops (F3) in terms of input J can be characterized by a more or less S-shaped function, for each F3 derived from the Yager, Dombi, and Fodor norms and co-norms. In this approach, J represents the neuron input. The other input K is wired to the complemental output (K=1-Q), thus an elementary fuzzy sequential unit with a single input and a single output is received. The algebraic F3 having linear J-Q(t+1) characteristics is added to the above three. The paper proposes the investigation of the possibility of constructing multilayer perceptrons from such real fuzzy hardware units. Each of the four candidates for F3-based neurons is examined for its training capability by evaluating and comparing the approximation capabilities for two different transcendental functions. Simulation results are presented.

UR - http://www.scopus.com/inward/record.url?scp=55249101975&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=55249101975&partnerID=8YFLogxK

U2 - 10.1109/FUZZY.2008.4630597

DO - 10.1109/FUZZY.2008.4630597

M3 - Conference contribution

AN - SCOPUS:55249101975

SN - 9781424418190

SP - 1683

EP - 1688

BT - IEEE International Conference on Fuzzy Systems

ER -