High storage capacity in the Hopfield model with auto-interactions-stability analysis

Recent studies point to the potential storage of a large number of patterns in the celebrated Hopfield associative memory model, well beyond the limits obtained previously. We investigate the properties of new fixed points to discover that they exhibit instabilities for small perturbations and are t...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. A, Mathematical and theoretical Mathematical and theoretical, 2017-11, Vol.50 (46), p.465001
Main Authors: Rocchi, Jacopo, Saad, David, Tantari, Daniele
Format: Article
Language:English
Subjects:
capacity
Hopfield model
recurrent neural networks
retrieval ability
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recent studies point to the potential storage of a large number of patterns in the celebrated Hopfield associative memory model, well beyond the limits obtained previously. We investigate the properties of new fixed points to discover that they exhibit instabilities for small perturbations and are therefore of limited value as associative memories. Moreover, a large deviations approach also shows that errors introduced to the original patterns induce additional errors and increased corruption with respect to the stored patterns.
ISSN:1751-8113
1751-8121
DOI:10.1088/1751-8121/aa8fd7