Parallel dynamics of the asymmetric extremely diluted Ashkin-Teller neural network
Disordered Systems and Neural Networks
2015-06-25 v1 Statistical Mechanics
Abstract
The parallel dynamics of the asymmetric extremely diluted Ashkin-Teller neural network is studied using signal-to-noise analysis techniques. Evolution equations for the order parameters are derived, both at zero and finite temperature. The retrieval properties of the network are discussed in terms of the four-spin coupling strength and the temperature. It is shown that the presence of a four-spin coupling enhances the retrieval quality.
Keywords
Cite
@article{arxiv.cond-mat/9911349,
title = {Parallel dynamics of the asymmetric extremely diluted Ashkin-Teller neural network},
author = {D. Bolle' and G. Jongen},
journal= {arXiv preprint arXiv:cond-mat/9911349},
year = {2015}
}
Comments
6 pages, 2 eps figures