On the equivalence of the Ashkin-Teller and the four-state Potts-glass models of neural networks
arXiv:cond-mat/0103585 · doi:10.1103/PhysRevE.64.067102
Abstract
We show that for a particular choice of the coupling parameters the Ashkin-Teller spin-glass neural network model with the Hebb learning rule and one condensed pattern yields the same thermodynamic properties as the four-state anisotropic Potts-glass neural network model. This equivalence is not seen at the level of the Hamiltonians.
3 pages, revtex, additional arguments presented