WIT Press

A Fuzzy Recurrent Neural Network Of Binary Neurons For Content Addressable Memory

Price

Free (open access)

Volume

20

Pages

11

Published

1998

Size

59 kb

Paper DOI

10.2495/AI980311

Copyright

WIT Press

Author(s)

Roelof K. Brouwer

Abstract

This paper is concerned with a proposal for a recurrent neural network of fuzzy neurons which may be used as a content addressable memory. The behavior of the fuzzy unit in the network is based on fuzzy logic in that each component of the binary input vector to the fuzzy neuron is compared to a number which represents the membership value for a 0 in that position. The results of the comparisons are then combined using a generalized mean function to produce a single number which is compared to a threshold. A training algorithm is developed based on an algorithm for linear inequalities described by Ho and Kashyap in a paper titled \“ An Algorithm for Linear Inequalities and its Applications”. The results obtained by simulation of this content addressable memory look promising enough to warrant furt

Keywords