k-winners-take-all neural net with Θ(1) time complexity.
Journal
IEEE Trans. Neural Networks
Journal Volume
8
Journal Issue
6
Pages
1557-1561
Date Issued
1997
Author(s)
Hsu, Tsong-Chih
Abstract
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.
Type
journal article