Fuzzy Neural Network Models for Classification

  • Authors:
  • Arun D. Kulkarni;Charles D. Cavanaugh

  • Affiliations:
  • Computer Science Department, The University of Texas at Tyler, Tyler, TX 75799, USA;Computer Science Department, The University of Texas at Tyler, Tyler, TX 75799, USA

  • Venue:
  • Applied Intelligence
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we combine neural networks with fuzzylogic techniques. We propose a fuzzy-neural network model for patternrecognition. The model consists of three layers. The first layer isan input layer. The second layer maps input features to thecorresponding fuzzy membership values, and the third layer implementsthe inference engine. The learning process consists of two phases.During the first phase weights between the last two layers areupdated using the gradient descent procedure, and during the secondphase membership functions are updated or tuned. As an illustrationthe model is used to classify samples from a multispectral satelliteimage, a data set representing fruits, and Iris data set.