A Modified Spreading Algorithm for Autoassociation in Weightless Neural Networks

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

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.
BibTeX
@inproceedings{browne1996modified,
  author = {Christopher John Browne and Joel de L. Pereira Castro Jr. and Amos J. Storkey},
  title = {{A Modified Spreading Algorithm for Autoassociation in Weightless Neural Networks}},
  booktitle = {ICANN},
  year = {1996},
  doi = {10.1007/3-540-61510-5\_97},
}

Loading related content...

Figure