K-WINNERS-TAKE-ALL NEURAL-NET WITH THETA(1) TIME-COMPLEXITY

Authors
HSU TC WANG SD
Citation
Tc. Hsu et Sd. Wang, K-WINNERS-TAKE-ALL NEURAL-NET WITH THETA(1) TIME-COMPLEXITY, IEEE transactions on neural networks, 8(6), 1997, pp. 1557-1561
Citations number
NO
Categorie Soggetti
Computer Application, Chemistry & Engineering","Engineering, Eletrical & Electronic","Computer Science Artificial Intelligence","Computer Science Hardware & Architecture","Computer Science Theory & Methods
Journal title
IEEE transactions on neural networks → ACNP
ISSN journal
10459227
Volume
8
Issue
6
Year of publication
1997
Pages
1557 - 1561
Database
ISI
SICI code
1045-9227(1997)8:6<1557:KNWTT>2.0.ZU;2-H
Abstract
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.