The Hopfield model on a sparse Erdös-Renyi graph

DOI10.1007/S10955-011-0167-1MaRDI QIDQ537898zbMATH OpenOpenAlexFDO

Authors Franck Vermet, M. Löwe

Publication date 23 May 2011

Published in Journal of Statistical Physics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10955-011-0167-1

zbMATH Keywords

Erdös-Renyi graphHopfield modelrandom matrixspectral theorystatistical mechanics

Mathematics Subject Classification ID

Random walks, random surfaces, lattice animals, etc. in equilibrium statistical mechanics (82B41)

Review text

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.

Recommendations

• Capacity of an associative memory model on random graph architectures
• scientific article; zbMATH DE number 919589
• Capacity of the Hopfield model
• The Little–Hopfield model on a sparse random graph
• Rigorous results on the thermodynamics of the dilute Hopfield model

Cites work

• Effect of connectivity in an associative memory model
• Fluctuations of the free energy in the diluted SK-model
• Gibbs measures and phase transitions on sparse random graphs
• scientific article; zbMATH DE number 1121933 (Why is no real title available?)
• Ising models on locally tree-like graphs
• Large deviations of the free energy in diluted mean-field spin-glass
• Lower bounds on the restitution error in the Hopfield model
• On the critical capacity of the Hopfield model.
• On the storage capacity of Hopfield models with correlated patterns
• Rigorous bounds on the storage capacity of the dilute Hopfield model
• Rigorous results for the Hopfield model with many patterns
• Rigorous results on the thermodynamics of the dilute Hopfield model
• Sharp upper bounds on perfect retrieval in the Hopfield model
• Spectral techniques applied to sparse random graphs
• The capacity of \(q\)-state Potts neural networks with parallel retrieval dynamics
• The capacity of the Hopfield associative memory
• The eigenvalues of random symmetric matrices
• The Largest Eigenvalue of Sparse Random Graphs
• The retrieval phase of the Hopfield model: A rigorous analysis of the overlap distribution

Cited in

(8)

• Multi-group binary choice with social interaction and a random communication structure -- a random graph approach
• Capacity of an associative memory model on random graph architectures
• scientific article; zbMATH DE number 1127070 (Why is no real title available?)
• Slowly evolving random graphs II: adaptive geometry in finite-connectivity Hopfield models
• The Little–Hopfield model on a sparse random graph
• Graph degree sequence solely determines the expected Hopfield network pattern stability
• Sparse connection density underlies the maximal functional difference between random and scale-free networks
• On the capacity of an associative memory model based on neural cliques

This page was built for publication: The Hopfield model on a sparse Erdös-Renyi graph

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q537898)