Title :
k-winners-take-all neural net with Θ(1) time complexity
Author :
Hsu, Tsong-Chih ; Wang, Sheng-De
Author_Institution :
Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
fDate :
11/1/1997 12:00:00 AM
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 Θ(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
Keywords :
computational complexity; convergence; neural nets; parallel processing; sorting; convergence; k-winners-take-all neural net; parallel processing; real-time processing; sorting machine; time complexity; Clocks; Control systems; Convergence; Hopfield neural networks; Neural networks; Process control; Sorting;
Journal_Title :
Neural Networks, IEEE Transactions on
