Author:

Keywords:

replica-symmetry-breaking, spin-glass, model, storage, dynamics, Science & Technology, Physical Sciences, Physics, Multidisciplinary, Physics, Mathematical, Physics, REPLICA-SYMMETRY-BREAKING, SPIN-GLASS, MODEL, STORAGE, DYNAMICS, Mathematical Physics

Abstract:

The thermodynamic and retrieval properties of the Ashkin-Teller neural network model storing an infinite number of patterns are examined in the replica-symmetric mean-field approximation. In particular, for linked patterns temperature-capacity phase diagrams are derived for different values of the two-neuron and four-neuron coupling strengths. This model can be considered as a particular non-trivial generalization of the Hopfield model and exhibits a number of interesting new features. Some aspects of replica-symmetry breaking are discussed.