INTERNATIONAL JOURNAL OF MODERN PHYSICS C, vol.13, no.2, pp.199-206, 2002 (SCI-Expanded)
The storage capacity of the Potts neural network is studied by using Monte Carlo techniques. It is observed that the critical storage capacity formula of Kanter fits well to our data. The increase of the correlation between the initial patterns reduces the storage capacity. This reduction in capacity is proportional to the percentage of correlations and inversely proportional to the number of orientations that the Potts neurons can possess.