Geometry of neural networks with asymmetric weight matrices

Author

Kakeya, Hideki ; Okabe, Yoichi

Author_Institution

Commun. Res. Lab., Minist. of Posts & Telecommun., Koganei, Japan

Volume

1

fYear

1999

fDate

1999

Firstpage

402

Abstract

Dynamics of Hopfield neural networks with asymmetric weights are elucidated from the geometrical viewpoint which is based on the eigenspace analysis of weight matrices. As the examples of asymmetric networks, cross-correlational associative memory and random networks are discussed. Complex dynamical behaviors of asymmetric networks such as spurious memory of cross-correlational associative memory and state transitions of random networks are explained geometrically. Also neuro-window method of asymmetric networks is proposed, which realizes capacity expansion and selective retrieval in cross-correlational associative memory

Keywords

Hopfield neural nets; content-addressable storage; matrix algebra; Hopfield neural networks; asymmetric networks; asymmetric weight matrices; asymmetric weights; cross-correlational associative memory; eigenspace analysis; neural networks geometry; neuro-window method; random networks; state transitions; Associative memory; Autocorrelation; Control systems; Eigenvalues and eigenfunctions; Geometry; Hopfield neural networks; Neural networks; Neurons; Symmetric matrices;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 1999. IEEE SMC '99 Conference Proceedings. 1999 IEEE International Conference on

Conference_Location

Tokyo

ISSN

1062-922X

Print_ISBN

0-7803-5731-0

Type

conf

DOI

10.1109/ICSMC.1999.814125

Filename

814125