Statics and dynamics of an Ashkin-Teller neural network with low loading
Disordered Systems and Neural Networks
2009-10-31 v2 Statistical Mechanics
q-bio
Abstract
An Ashkin-Teller neural network, allowing for two types of neurons is considered in the case of low loading as a function of the strength of the respective couplings between these neurons. The storage and retrieval of embedded patterns built from the two types of neurons, with different degrees of (in)dependence is studied. In particular, thermodynamic properties including the existence and stability of Mattis states are discussed. Furthermore, the dynamic behaviour is examined by deriving flow equations for the macroscopic overlap. It is found that for linked patterns the model shows better retrieval properties than a corresponding Hopfield model.
Keywords
Cite
@article{arxiv.cond-mat/9801284,
title = {Statics and dynamics of an Ashkin-Teller neural network with low loading},
author = {D. Bolle and P. Kozlowski},
journal= {arXiv preprint arXiv:cond-mat/9801284},
year = {2009}
}
Comments
20 pages, 6 figures, Latex with postscript figures in one tar.gz file