Title :
A k-winners-take-all neural net
Author :
Calvert, Bruce D. ; Marinov, Corneliu A.
Author_Institution :
Dept. of Math., Auckland Univ., New Zealand
Abstract :
An analog Hopfield type neural network is given, that identifies the k largest components of a list d of N real numbers. The list to be processed is a summand of the input currents of the neurons, and the network is started from 0. We provide easily computable restrictions on the parameters. The trajectories are shown to eventually have positive components precisely in the positions given by the k largest elements in the input list
Keywords :
Hopfield neural nets; analog Hopfield type neural network; k-winners-take-all neural net; Associative memory; Circuit synthesis; Decision making; Hopfield neural networks; Mathematics; Network synthesis; Neural networks; Neurons; Switches; Telecommunication control;
Conference_Titel :
Decision and Control, 2000. Proceedings of the 39th IEEE Conference on
Conference_Location :
Sydney, NSW
Print_ISBN :
0-7803-6638-7
DOI :
10.1109/CDC.2000.912254
