Connectivity graphs and the performance of sparse associative memory models

Author

Chen, Weiliang ; Adams, Rod ; Calcraft, Lee ; Steuber, Volker ; Davey, Neil

Author_Institution

Sci. & Technol. Res. Inst., Univ. of Hertfordshire, Hatfield

fYear

2008

fDate

1-8 June 2008

Firstpage

2742

Lastpage

2749

Abstract

This paper investigates the relationship between network connectivity and associative memory performance using high capacity associative memory models with different types of sparse networks. We found that the clustering of the network, measured by Clustering Coefficient and Local Efficiency, have a strong linear correlation to its performance as an associative memory. This result is important since a purely static measure of network connectivity appears to determine an important dynamic property of the network.

Keywords

content-addressable storage; graph theory; neural nets; pattern clustering; associative memory performance; clustering coefficient; connectivity graphs; high capacity associative memory models; linear correlation; local efficiency; network clustering; network connectivity; sparse associative memory models; sparse networks; Associative memory; Degradation; Neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on

Conference_Location

Hong Kong

ISSN

1098-7576

Print_ISBN

978-1-4244-1820-6

Electronic_ISBN

1098-7576

Type

conf

DOI

10.1109/IJCNN.2008.4634183

Filename

4634183