The three-dimensional rotation neural network

The storage capacity of the three-dimensional rotation neural network model is discussed by using the signal-to-noise theory. Some results discussed in the Hopfield model, the complex phasor model and the Hamilton neural network are obtained. Compared to other multistate neural networks, a novel property of the model is that the storage capacity for a fixed neuronal state varies with the different combinations of numbers of rotation angles and axes. The maximum storage capacity can be obtained for a special combination of numbers of rotation angles and axes.