UNIGE document Scientific Article
previous document  unige:90976  next document
add to browser collection
Title

Phase diagrams and the instability of the spin glass states for the diluted Hopfield neural network model

Authors
Naef, Jean-Pierre
Published in Journal de Physique I. 1992, vol. 2, no. 9, p. 1791-1801
Abstract The replica-symmetric order parameter equations derived in [2, 4] for the symmetrically diluted Hopfield neural network model [1] are solved for different degrees of dilution. The dilution is random but symmetric. Phase diagrams are presented for c=1, 0.1, 0.001 and $c o 0$, where c is the fractional connectivity. The line $T_{ m c}$ where the memory states become global minima (having lower free energy than the spin glass states) is also found for different values of c. It is found that the effect of dilution is to destabilize the spin glass states and the line $T_{ m c}$ is driven rapidly towards the line $T_{ m M}$; the phase transition line where the memory states first stabilize. All the results are derived in the context of replica symmetry so are expected to be incorrect in certain parts of the phase diagram (the error increasing the further below the replica symmetry breaking lines we are) but our results do suggest in a general way that dilution, even in small quantities, increases the stability of the memory states with respect to the spin glass states.
Identifiers
Full text
Article (Published version) (1.2 MB) - document accessible for UNIGE members only Limited access to UNIGE
Other version: http://www.edpsciences.org/10.1051/jp1:1992245
Structures
Citation
(ISO format)
CANNING, Andréw Magnus, NAEF, Jean-Pierre. Phase diagrams and the instability of the spin glass states for the diluted Hopfield neural network model. In: Journal de Physique I, 1992, vol. 2, n° 9, p. 1791-1801. https://archive-ouverte.unige.ch/unige:90976

37 hits

1 download

Update

Deposited on : 2017-01-11

Export document
Format :
Citation style :