For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
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
Publication Date: 1993/12/25
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>>
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.