Abstract
Convergence time in Hopfield attractor neural network with parallel dynamics is investigated by computer simulation of networks of extremely large size (up to the number of neurons N = 105). Special algorithm is used to avoid storing in the computer memory both connection matrix and the set of stored prototypes. Thus, the size of the simulated network is restricted only by the processing time. It is shown that asymptotically for \math the number of time steps S which are required to reach attractor in the vicinity of the recalled prototype is proportional to \math where power index \math