The swapping algorithm for the Hopfield model with two patterns

DOI10.1016/J.SPA.2009.06.007MaRDI QIDQ734648zbMATH OpenOpenAlexFDO

Authors Franck Vermet, M. Löwe

Publication date 13 October 2009

Published in Stochastic Processes and their Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.spa.2009.06.007

zbMATH Keywords

Metropolis algorithmMarkov chain Monte Carlo methodswapping algorithmHopfield modelspin glasses

Mathematics Subject Classification ID

Interacting random processes; statistical mechanics type models; percolation theory (60K35) 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)

Recommendations

• On the swapping algorithm
• On swapping and simulated tempering algorithms.
• Torpid mixing of the swapping chain on some simple spin glass models
• Mixing times for the swapping algorithm on the Blume-Emery-Griffiths model
• On the Hopfield algorithm. Foundations and examples

Cites work

• scientific article; zbMATH DE number 420886 (Why is no real title available?)
• scientific article; zbMATH DE number 1303210 (Why is no real title available?)
• scientific article; zbMATH DE number 1303211 (Why is no real title available?)
• Annealing Markov Chain Monte Carlo with Applications to Ancestral Inference
• Comparison theorems for reversible Markov chains
• Equation of state calculations by fast computing machines
• Geometric bounds for eigenvalues of Markov chains
• Gibbs states of the Hopfield model in the regime of perfect memory
• Logarithmic Sobolev inequalities for finite Markov chains
• Neural networks and physical systems with emergent collective computational abilities
• On the storage capacity of Hopfield models with correlated patterns
• On the swapping algorithm
• Some rigorous results on the Hopfield neural network model
• The capacity of \(q\)-state Potts neural networks with parallel retrieval dynamics
• The capacity of the Hopfield associative memory
• The storage capacity of the Hopfield model and moderate deviations
• Torpid mixing of simulated tempering on the Potts model
• What do we know about the Metropolis algorithm?

Cited in

(5)

• Equi-energy sampling does not converge rapidly on the mean-field Potts model with three colors close to the critical temperature
• Mixing times for the swapping algorithm on the Blume-Emery-Griffiths model
• On the swapping algorithm
• Some remarks on replicated simulated annealing
• Torpid mixing of the swapping chain on some simple spin glass models

This page was built for publication: The swapping algorithm for the Hopfield model with two patterns

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q734648)