Thermodynamics of fully connected Blume-Emery-Griffiths neural networks
Disordered Systems and Neural Networks
2009-11-07 v1
Abstract
The thermodynamic and retrieval properties of fully connected Blume-Emery-Griffiths networks, storing ternary patterns, are studied using replica mean-field theory. Capacity-temperature phase diagrams are derived for several values of the pattern activity. It is found that the retrieval phase is the largest in comparison with other three-state neuron models. Furthermore, the meaning and stability of the so-called quadrupolar phase is discussed as a function of both the temperature and the pattern activity. Where appropriate, the results are compared with the diluted version of the model.
Keywords
Cite
@article{arxiv.cond-mat/0210237,
title = {Thermodynamics of fully connected Blume-Emery-Griffiths neural networks},
author = {D. Bolle and T. Verbeiren},
journal= {arXiv preprint arXiv:cond-mat/0210237},
year = {2009}
}
Comments
13 pages, 6 figures, iopart style