The Hopfield model on a sparse Erdös-Renyi graph (Q537898)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: The Hopfield model on a sparse Erdös-Renyi graph |
scientific article; zbMATH DE number 5898924
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | The Hopfield model on a sparse Erdös-Renyi graph |
scientific article; zbMATH DE number 5898924 |
Statements
The Hopfield model on a sparse Erdös-Renyi graph (English)
0 references
23 May 2011
0 references
The storage capacity of the Hopfield model on a sparse \(G(N,p)\) random graph is analyzed. The Hopfield model is well known to be a spin glass on the one hand, but also to model a neural network, on the other. It is proved that the storage capacity is proportional to \(\alpha p N\) (with \(\alpha\leq \alpha_c=0.03\)) in the entire regime where the corresponding random graph is asymptotically connected.
0 references
Hopfield model
0 references
Erdös-Renyi graph
0 references
random matrix
0 references
spectral theory
0 references
statistical mechanics
0 references
0 references
0.8561081886291504
0 references
0.8160148859024048
0 references
0.8124280571937561
0 references
0.8116137981414795
0 references
