k-winners-take-all neural net with /spl Theta/(1) time complexity
Tsong-Chih Hsu, Sheng‐De Wang · IEEE Transactions on Neural Networks · 1997
In this article we present a k-winners-take-all (k-WTA) neural net that is established based on the concept of the constant time sorting machine by Hsu and Wang. It fits some specific applications, such as real-time processing, since its Theta(1) time complexity is independent to the problem size. The proposed k-WTA neural net produces the solution in constant time while the Hopfield network requires a relatively long transient to converge to the solution from some initial states.