On rates of convergence for the overlap in the Hopfield model

DOI10.17879/58269754868MaRDI QIDQ3464612zbMATHFDO

Authors Peter Eichelsbacher, Bastian Martschink

Publication date 27 January 2016

Full work available at URL https://arxiv.org/abs/1303.5252

zbMATH Keywords

overlapcentral limit theoremconvergence ratesHopfield model

Mathematics Subject Classification ID

Central limit and other weak theorems (60F05) Interacting random processes; statistical mechanics type models; percolation theory (60K35) Statistical mechanics of random media, disordered materials (including liquid crystals and spin glasses) (82D30) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Abstract: We consider the Hopfield model with $n$ neurons and an increasing number $p=p(n)$ of randomly chosen patterns and use Stein's method to obtain rates of convergence for the central limit theorem of overlap parameters, which holds for every fixed choice of the overlap parameter for almost all realisations of the random patterns.

Recommendations

• A central limit theorem for the overlap in the Hopfield model
• scientific article; zbMATH DE number 1121925
• On the Hopfield model at the critical temperature
• scientific article; zbMATH DE number 1003686
• The fluctuations of the overlap in the Hopfield model with finitely many patterns at the critical temperature

Cited in

(3)

• scientific article; zbMATH DE number 152119 (Why is no real title available?)
• The retrieval phase of the Hopfield model: A rigorous analysis of the overlap distribution
• Berry-Esseen bounds in the inhomogeneous Curie-Weiss model with external field

This page was built for publication: On rates of convergence for the overlap in the Hopfield model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3464612)