Multilayer Pereeptron Implemented by Fuzzy Flip-Flops

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 (F 3 ) in terms of input J can be characterized by a more...

Full description

Saved in:
Bibliographic Details
Main Authors: Lovassy, R., Koczy, L.T., Gal, L.
Format: Conference Proceeding
Language:English
Subjects:
Conferences
Fuzzy systems
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 (F 3 ) in terms of input J can be characterized by a more or less S-shaped function, for each F 3 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 F 3 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 F 3 -based neurons is examined for its training capability by evaluating and comparing the approximation capabilities for two different transcendental functions. Simulation results are presented.
ISSN:1098-7584
DOI:10.1109/FUZZY.2008.4630597