The convergence of Hamming memory networks

1 July 1991

journal article
Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks

Vol. 2 (4) , 449-457
https://doi.org/10.1109/72.88164

Abstract

The convergence properties of Hamming memory networks are studied. It is shown how to construct the network so that it probably converges to an appropriate result, and a tight bound is given on the convergence time. The bound on the convergence time is largest when several stored vectors are at the minimum distance from the input vector. For random binary vectors, the probability for such situations to occur is not small. With a specific choice of parameter values, the worst-case convergence time is on the order of p ln (pn), where p is the memory capacity and n is the vector length. By allowing the connection weights to change during the computation, the convergence time can be decreased considerably.

Keywords

This publication has 6 references indexed in Scilit:

Internal representations for associative memory
Biological Cybernetics, 1988
A maximum overlap neural network for pattern recognition
Physics Letters A, 1987
An introduction to computing with neural nets
IEEE ASSP Magazine, 1987
Cortico-thalamic organization and memory
Proceedings of the Royal Society of London. B. Biological Sciences, 1964
Learning matrices and their applications
IEEE Transactions on Electronic Computers, 1963
Die Lernmatrix
Biological Cybernetics, 1961