The Ashkin-Teller neural network near saturation

The thermodynamic and retrieval properties of the Ashkin-Teller neural netw ork model storing an infinite number of patterns are examined in the replic a-symmetric mean-field approximation. In particular, for linked patterns te mperature-capacity phase diagrams are derived for different values of the t wo-neuron and four-neuron coupling strengths. This model can be considered as a particular non-trivial generalization of the Hopfield model and exhibi ts a number of interesting new features. Some aspects of replica-symmetry b reaking are discussed.