Title
Design of a K-Winners-Take-All Model With a Binary Spike Train.
Abstract
A continuous-time K-winners-take-all (KWTA) neural model that can identify the largest K of N inputs, where command signal 1 ≤ K <; N is described. The model is given by a differential equation where the spike train is a sum of delta functions. A functional block-diagram of the model includes N feed-forward hard-limiting neurons and one feedback neuron, used to handle input dynamics. The existence...
Year
DOI
Venue
2019
10.1109/TCYB.2018.2839691
IEEE Transactions on Cybernetics
Keywords
Field
DocType
Computational modeling,Mathematical model,Convergence,Artificial neural networks,Analytical models,Trajectory,Hardware
Convergence (routing),Applied mathematics,Uniqueness,Differential equation,Mathematical optimization,Spike train,State variable,Initial value problem,Mathematical model,Mathematics,Binary number
Journal
Volume
Issue
ISSN
49
8
2168-2267
Citations 
PageRank 
References 
3
0.38
0
Authors
2
Name
Order
Citations
PageRank
Pavlo V. Tymoshchuk1152.00
Wunsch II Donald C.2135491.73