https://doi.org/10.1140/epjb/e2005-00328-7
The Blume-Emery-Griffiths neural network with synchronous updating and variable dilution
Instituut voor Theoretische Fysica, Katholieke Universiteit Leuven, Celestijnenlaan 200 D, 3001 Leuven, Belgium
Corresponding authors: a desire.bolle@fys.kuleuven.be - b Jordi.Busquets@fys.kuleuven.be
Received:
13
May
2005
Revised:
7
July
2005
Published online:
11
October
2005
The thermodynamic and retrieval properties of the Blume-Emery-Griffiths neural network with synchronous updating and variable dilution are studied using replica mean-field theory. Several forms of dilution are allowed by pruning the different types of couplings present in the Hamiltonian. The appearance and properties of two-cycles are discussed. Capacity-temperature phase diagrams are derived for several values of the pattern activity. The results are compared with those for sequential updating. The effect of self-coupling is studied. Furthermore, the optimal combination of dilution parameters giving the largest critical capacity is obtained.
PACS: 05.20.-y – Classical statistical mechanics / 64.60.Cn – Order-disorder transformations; statistical mechanics of model systems / 87.18.Sn – Neural networks
© EDP Sciences, Società Italiana di Fisica, Springer-Verlag, 2005
