Information storage capacity of incompletely connected associative memories

Citation data:

Neural Networks, ISSN: 0893-6080, Vol: 11, Issue: 5, Page: 869-876

Publication Year:
1998
Usage 393
Downloads 291
Abstract Views 102
Captures 11
Readers 11
Citations 21
Citation Indexes 21
Repository URL:
https://digitalcommons.calpoly.edu/csse_fac/18; https://works.bepress.com/fkurfess/20
DOI:
10.1016/s0893-6080(98)00035-5
Author(s):
Bosch, Holger; Kurfess, Franz J.
Publisher(s):
Elsevier BV
Tags:
Computer Science; Neuroscience; Associative memory; Information storage capacity; Incomplete interconnectivity; Hetero-association; Auto-association; Hebbian learning; Retrieval strategy; Sparse coding.; Computer Sciences
article description
In this paper, the memory capacity of incompletely connected associative memories is investigated. First, the capacity is derived for memories with fixed parameters. Optimization of the parameters yields a maximum capacity between 0.53 and 0.69 for hetero-association and half of it for autoassociation improving previously reported results. The maximum capacity grows with increasing connectivity of the memory and requires sparse input and output patterns. Further, parameters can be chosen in such a way that the information content per pattern asymptotically approaches 1 with growing size of the memory.