An Autocorrelation Associative Neural Network with Self-Feedbacks

Hiroshi UEDA  Masaya OHTA  Akio OGIHARA  Kunio FUKUNAGA  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E76-A   No.12   pp.2072-2075
Publication Date: 1993/12/25
Online ISSN: 
Print ISSN: 0916-8508
Type of Manuscript: Special Section LETTER (Special Section of Letters Selected from the 1993 IEICE Fall Conference)
neural network,  autocorrelation associative memory,  self-feedback,  spurious states,  

Full Text: PDF>>
Buy this Article

In this article, the autocorrelation associative neural network that is one of well-known applications of neural networks is improved to extend its capacity and error correcting ability. Our approach of the improvement is based on the consideration that negative self-feedbacks remove spurious states. Therefore, we propose a method to determine the self-feedbacks as small as possible within the range that all stored patterns are stable. A state transition rule that enables to escape oscillation is also presented because the method has a possibility of falling into oscillation. The efficiency of the method is confirmed by means of some computer simulations.