The swapping algorithm for the Hopfield model with two patterns
The so-called swapping algorithm was designed to simulate from spin glass distributions, among others. In this note we show that it mixes rapidly, in a very simple disordered system, the Hopfield model with two patterns.
Year of publication: |
2009
|
---|---|
Authors: | Löwe, Matthias ; Vermet, Franck |
Published in: |
Stochastic Processes and their Applications. - Elsevier, ISSN 0304-4149. - Vol. 119.2009, 10, p. 3471-3493
|
Publisher: |
Elsevier |
Keywords: | Swapping algorithm Metropolis algorithm Hopfield model Markov chain Monte Carlo methods Neural networks Spin glasses |
Saved in:
Online Resource
Saved in favorites
Similar items by person
-
The capacity of q-state Potts neural networks with parallel retrieval dynamics
Löwe, Matthias, (2007)
-
The storage capacity of the Hopfield model and moderate deviations
Löwe, Matthias, (2005)
-
Gaussian fluctuations for sample covariance matrices with dependent data
Friesen, Olga, (2013)
- More ...