The swapping algorithm for the Hopfield model with two patterns

DOI10.1016/j.spa.2009.06.007zbMath1178.82060MaRDI QIDQ734648

Franck Vermet, Matthias Loewe

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

Markov chain Monte Carlo method; spin glasses; Hopfield model; Metropolis algorithm; swapping algorithm

Mathematics Subject Classification ID

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

82B44: Disordered systems (random Ising models, random Schrödinger operators, etc.) in equilibrium statistical mechanics

82C32: Neural nets applied to problems in time-dependent statistical mechanics

Related Items

Mixing times for the Swapping Algorithm on the Blume-Emery-Griffiths model

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Some rigorous results on the Hopfield neural network model
• Geometric bounds for eigenvalues of Markov chains
• What do we know about the Metropolis algorithm?
• On the storage capacity of Hopfield models with correlated patterns
• Comparison theorems for reversible Markov chains
• Gibbs states of the Hopfield model in the regime of perfect memory
• The capacity of \(q\)-state Potts neural networks with parallel retrieval dynamics
• The storage capacity of the Hopfield model and moderate deviations
• Logarithmic Sobolev inequalities for finite Markov chains
• The capacity of the Hopfield associative memory
• On the swapping algorithm
• Annealing Markov Chain Monte Carlo with Applications to Ancestral Inference
• Equation of State Calculations by Fast Computing Machines
• Neural networks and physical systems with emergent collective computational abilities.