Shift-Invariant Associative Memory Based on Homogeneous Neural Networks

Hiromi MIYAJIMA  Noritaka SHIGEI  Shuji YATSUKI  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E88-A   No.10   pp.2600-2606
Publication Date: 2005/10/01
Online ISSN: 
DOI: 10.1093/ietfec/e88-a.10.2600
Print ISSN: 0916-8508
Type of Manuscript: Special Section PAPER (Special Section on Nonlinear Theory and its Applications)
associative memory,  shift-invariant,  homogeneous neural networks,  memory capacity,  

Full Text: PDF(332.4KB)>>
Buy this Article

This paper proposes homogeneous neural networks (HNNs), in which each neuron has identical weights. HNNs can realize shift-invariant associative memory, that is, HNNs can associate not only a memorized pattern but also its shifted ones. The transition property of HNNs is analyzed by the statistical method. We show the probability that each neuron outputs correctly and the error-correcting ability. Further, we show that HNNs cannot memorize over the number,, of patterns, where m is the number of neurons and k is the order of connections.