Capacity of Semi-Orthogonally Associative Memory Neural Network Model

Xin-Min HUANG  Yasumitsu MIYAZAKI  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E79-D   No.1   pp.72-81
Publication Date: 1996/01/25
Online ISSN: 
DOI: 
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Bio-Cybernetics and Neurocomputing
Keyword: 
neurocomputing,  neural network,  pattern recognition,  associative memory,  

Full Text: PDF>>
Buy this Article




Summary: 
Semi-Orthogonally Associative Memory neural network model (SAM) uses the orthogonal vectors in Un = {-1, 1}n as its characteristic patterns. It is necessary to select the optimum characteristic parameter n so as to increase the efficiency of this model used. This paper investigates the dynamic behavior and error correcting capability of SAM by statistical neurodynamics, and demonstrates that there exists a convergence criterion in tis recalling processes. And then, making use of these results, its optimum characteristic parameter is deduced. It is proved that, in the statistical sense, its recalling outputs converge to the desired pattern when the initial similar probability is larger than the convergence criterion and not true otherwise. For a SAM with N neurons, when its characteristic parameter is optimum, its memory capacity is N/2 ln ln N, the information storage capacity per connection weight is larger than 9/23 (bits/weight) and the radius of attractive basin of non-spurious stable state is about 0.25N. Computer simulations are done on this model and the simulation results are consistent with the results of theoretical analyses.