
For FullText 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 Memory which Has an Energy Function of Higher Order
Sadayuki MURASHIMA Takayasu FUCHIDA Toshihiro IDA Takayuki TOYOHIRA Hiromi MIYAJIMA
Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Vol.E78A
No.3
pp.424430 Publication Date: 1995/03/25
Online ISSN:
DOI:
Print ISSN: 09168508 Type of Manuscript: PAPER Category: Neural Networks Keyword: autocorrelation, associative memory, energy function, higher order,
Full Text: PDF>>
Summary:
A noise tolerant autocorrelation associative memory is proposed. An associated energy function is formed by a multiplication of plural Hopfield's energy functions each of which includes single pattern as its energy minimum. An asynchronous optimizing algorithm of the whole energy function is also presented based on the binary neuron model. The advantages of this new associative memory are that the orthogonality relation among patterns does not need to be satisfied and each stored pattern has a large basin of attraction around itself. The computer simulations show a fairly good performance of associative memory for arbitrary pattern vectors which are not orthogonal to each other.

