A Modified Spreading Algorithm for Autoassociation in Weightless Neural Networks

Download PDF
Open Webpage

Christopher John Browne, Joel de L. Pereira Castro Jr., Amos J. Storkey

Published: 1996, Last Modified: 08 Jan 2026ICANN 1996EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: This paper describes a problem with the conventional Hamming metric spreading algorithm often employed in weightless neural networks. The algorithm can cause incorrect classifications in some cases where a section of the neuron input vector is noise. The conditions under which such error occurs are described and a modified spreading algorithm proposed to overcome this problem has its validity demonstrated theoretically and tested in two practical applications.