Open Access
August 2015 Capacity of an associative memory model on random graph architectures
Matthias Löwe, Franck Vermet
Bernoulli 21(3): 1884-1910 (August 2015). DOI: 10.3150/14-BEJ630


We analyze the storage capacity of the Hopfield models on classes of random graphs. While such a setup has been analyzed for the case that the underlying random graph model is an Erdös–Renyi graph, other architectures, including those investigated in the recent neuroscience literature, have not been studied yet. We develop a notion of storage capacity that highlights the influence of the graph topology and give results on the storage capacity for not too irregular random graph models. The class of models investigated includes the popular power law graphs for some parameter values.


Download Citation

Matthias Löwe. Franck Vermet. "Capacity of an associative memory model on random graph architectures." Bernoulli 21 (3) 1884 - 1910, August 2015.


Received: 1 January 2014; Published: August 2015
First available in Project Euclid: 27 May 2015

zbMATH: 1326.60015
MathSciNet: MR3352065
Digital Object Identifier: 10.3150/14-BEJ630

Keywords: associative memory , Hopfield model , powerlaw graphs , Random graphs , Random matrix , Spectral theory , statistical mechanics

Rights: Copyright © 2015 Bernoulli Society for Mathematical Statistics and Probability

Vol.21 • No. 3 • August 2015
Back to Top