An Improvement of the Pseudoinverse Rule with Diagonal Elements

Hiroshi UEDA  Masaya OHTA  Akio OGIHARA  Kunio FUKUNAGA  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E77-A   No.6   pp.1007-1014
Publication Date: 1994/06/25
Online ISSN: 
DOI: 
Print ISSN: 0916-8508
Type of Manuscript: Special Section PAPER (Special Section of Papers Selected from 1993 Joint Technical Conference on Circuits/Systems, Computers and Communications (JTC-CSCC'93))
Category: Neural Networks
Keyword: 
neural network,  pseudoinverse rule,  self-feedback,  spurious states,  

Full Text: PDF>>
Buy this Article



Summary: 
A pseudoinverse rule, one of major rule to determine a weight matrix for associative memory, has large capacity comparing with other determining rules. However, it is wellknown that the rule has small domains of attraction of memory vectors on account of many spurious states. In this paper, we try to improve the problem by means of subtracting a constant from all diagonal elements of a weight matrix. By this method, many spurious states disappear and eigenvectors with negative eigenvalues are introduced for the orthocomplement of the subspace spanned by memory vectors. This method can be applied to two types of networks: binary network and analog network. Some computer simulations are performed for both two models. The results of the simulations show our improvement is effective to extend error correcting ability for both networks.