In this letter we present a kappa-Winners-Take-All (kappa-WTA) neural
net that is established based on the concept of the constant time sort
ing machine by Hsu and Wang [1]. It fits some specific applications, s
uch as real-time processing, since its Theta(1) time complexity is ind
ependent to the problem size, The proposed kappa-WTA neural net produc
es the solution in constant time while the Hopfield network requires a
relatively long transient to converge to the solution from some initi
al states.