An almost sure large deviation principle for the Hopfield model

DOI10.1214/AOP/1065725188MaRDI QIDQ2565363zbMATH OpenOpenAlexFDO

Authors Anton Bovier, V. Gayrard

Publication date 24 September 1997

Published in The Annals of Probability (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/cond-mat/9504003

zbMATH Keywords

large deviations principleHopfield modeloverlap parameters

Mathematics Subject Classification ID

Large deviations (60F10) Disordered systems (random Ising models, random Schrödinger operators, etc.) in equilibrium statistical mechanics (82B44) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Abstract: We prove a large deviation principle for the finite dimensional marginals of the Gibbs distribution of the macroscopic `overlap'-parameters in the Hopfield model in the case where the number of random patterns, $M$, as a function of the system size $N$ satisfies $limsupM(N)/N=0$. In this case the rate function (or free energy as a function of the overlap parameters) is independent of the disorder for almost all realization of the patterns and given by an explicit variational formula.

Recommendations

• Large deviation principles for the Hopfield model and the Kac-Hopfield model
• scientific article; zbMATH DE number 1191604
• Moderate deviations for the overlap parameter in the Hopfield model
• scientific article; zbMATH DE number 1121925

Cited in

(12)

• scientific article; zbMATH DE number 152119 (Why is no real title available?)
• Extreme value behavior in the Hopfield model
• Moderate deviations for the overlap parameter in the Hopfield model
• Exponential inequalities and convergence of moments in the replica-symmetric regime of the Hopfield model.
• A central limit theorem for the overlap in the Hopfield model
• High temperature asymptotics of orthogonal mean-field spin glasses
• scientific article; zbMATH DE number 1121933 (Why is no real title available?)
• On the storage capacity of Hopfield models with correlated patterns
• Fluctuations of the free energy in the high temperature Hopfield model
• Ordered overlaps in disordered mean-field models
• Quenched large deviation principle for the overlap of a \(p\)-spins system
• A spectral approach to Hebbian-like neural networks

This page was built for publication: An almost sure large deviation principle for the Hopfield model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2565363)