Paper Authors

Abstract

NOTE: The first page of text has been automatically extracted and included below in lieu of an abstract

“ 1 Session 2520

Neural Networks and Fuzzy Systems: A Relationship Between Them

E. J. Mastascusa Electrical Engineering Department Bucknell University Lewisburg, PA 17837

Introduction

Neural networks and fuzzy systems have much in common, but can be approached and taught as though they were completely disparate subjects. Explicit links between the two subjects can aid students as they grapple with both subjects ‘ . Shared structures and concepts explicitly presented can be an aid to learning.

In this paper we will present a bridge between the two subject areas. We propose that this bridge is a useful paradigm that helps students learning fuzzy systems and neural networks.

The Neural Network

We begin by considering a three layer neural network. The general structure of such a network is given in Figure 1, which emphasizes the inputs and the input layer of neurons.

Inputs and Input Layer

Figure 1 A Three Layer Neural Network Structure

This particular structure, a three layer feedforward neural network is a starting point for other, more complex, neural network structures. However, this particular network is related to a fuzzy system because this network implements a rule base for a fuzzy system and the rule base can be determined from an examination of the network and the weights associated with the network connecting links. This link between the neural network and an associated fuzzy system rule base is not presented in either neural network texts or fuzzy systems texts.

{~x~j 1996 ASEE Annual Conference Proceedings ?yllllclll’..’ .

• Citation

• Format
  • APA
  • APA - LaTeX bibitem
  • MLA
  • MLA - LaTeX bibitem
  • Bibtex
  • EndNote - RIS

Mastascusa, E. J. (1996, June), Neural Networks And Fuzzy Systems: A Relationship Between Them Paper presented at 1996 Annual Conference, Washington, District of Columbia. 10.18260/1-2--6203