This paper proposes a discrete recurrent neural network model to implement
winner-take-all function, Tills network model has simple organizations and
clear dynamic behaviors. The dynamic properties of the proposed winner-take
-all networks are studied in detail. Simulation results are gi, en to show
network performance. Since the network model is formulated as discrete time
systems, it has advantages for computer simulations over digital simulatio
ns of continuous time neural network model. Thus they can be easily impleme
nted in digital hardware.