DocumentCode
3174274
Title
Effect of connectivity in associative memory models
Author
Komlós, János ; Paturi, Ramamohan
Author_Institution
California Univ., San Diego, La Jolla, CA, USA
fYear
1988
fDate
24-26 Oct 1988
Firstpage
138
Lastpage
147
Abstract
The authors investigate how good connectivity properties translate into good error-correcting behavior in sparse networks of threshold elements. They determine how the eigenvalues of the interconnection graph (which in turn reflect connectivity properties) relate to the quantities, number of items stored, amount of error-correction, radius of attraction, and rate of convergence in an associative memory model consisting of a sparse network of threshold elements or neurons
Keywords
content-addressable storage; eigenvalues and eigenfunctions; neural nets; associative memory models; connectivity; eigenvalues; error-correcting; interconnection graph; neurons; rate of convergence; sparse networks; threshold elements; Associative memory; Biological system modeling; Biological systems; Biology computing; Brain modeling; Humans; Learning systems; Neurons; Power system modeling; Vectors;
fLanguage
English
Publisher
ieee
Conference_Titel
Foundations of Computer Science, 1988., 29th Annual Symposium on
Conference_Location
White Plains, NY
Print_ISBN
0-8186-0877-3
Type
conf
DOI
10.1109/SFCS.1988.21932
Filename
21932
Link To Document