Sequence Processing Neural Network withQ-States Monotonic Transfer Function
Katsuki Katayama, Tsuyoshi Horiguchi · Progress of Theoretical Physics Supplement · 2005
Storage capacity as for retrieval of sequences of binary patterns is investigated for a fully connected neural network with Q (>2)-states. By using a generating-function method of path-integral representation, we find that the network with Q-states monotonic transfer function retrieves more sequences of the stored patterns than that with a binary monotonic transfer function at zero temperature, if the control parameter is chosen optimally. We compare the results obtained by the analytic method with those by numerical simulations.