Parallel dynamics of the asymmetric extremely diluted Ashkin-Teller neural network
arXiv:cond-mat/9911349 · doi:10.1007/s100510070192
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.
6 pages, 2 eps figures