An Improvement of the Pseudoinverse Rule with Diagonal Elements
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.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E77-A No.6 pp.1007-1014
- Publication Date
- 1994/06/25
- Publicized
- Online ISSN
- DOI
- 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
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Hiroshi UEDA, Masaya OHTA, Akio OGIHARA, Kunio FUKUNAGA, "An Improvement of the Pseudoinverse Rule with Diagonal Elements" in IEICE TRANSACTIONS on Fundamentals,
vol. E77-A, no. 6, pp. 1007-1014, June 1994, doi: .
Abstract: 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.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e77-a_6_1007/_p
Copy
@ARTICLE{e77-a_6_1007,
author={Hiroshi UEDA, Masaya OHTA, Akio OGIHARA, Kunio FUKUNAGA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={An Improvement of the Pseudoinverse Rule with Diagonal Elements},
year={1994},
volume={E77-A},
number={6},
pages={1007-1014},
abstract={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.},
keywords={},
doi={},
ISSN={},
month={June},}
Copy
TY - JOUR
TI - An Improvement of the Pseudoinverse Rule with Diagonal Elements
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1007
EP - 1014
AU - Hiroshi UEDA
AU - Masaya OHTA
AU - Akio OGIHARA
AU - Kunio FUKUNAGA
PY - 1994
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E77-A
IS - 6
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - June 1994
AB - 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.
ER -
English
