Paper Info
Title
A Continuous-Time Model of Analogue K-Winners-Take-All Neural Circuit.
Abstract
A continuous-time model of analogue K-winners-take-all (KWTA) neural circuit which is capable to extraction the K largest from any finite value N unknown distinct inputs, where 1 <= K < N, is presented. The model is described by one state equation with discontinuous right-hand side and output equation. A corresponding functional block diagram of the model is given as N feedforward and one feedback hardlimiting neurons, which is used to determine the dynamic shift of inputs. The model combines such properties as high accuracy and convergence speed, low computational and hardware implementation complexity, and independency on initial conditions. Simulation examples demonstrating the model performance are provided.
Year
DOI
Venue
2012
10.1007/978-3-642-32909-8_10
Communications in Computer and Information Science
Keywords
Field
DocType
Continuous-time model,State equation,Functional block-diagram,Hardlimiting neuron,Analogue K-winners-take-all neural circuit
Convergence (routing),Equation of state,Control theory,Computer science,Time model,Functional block diagram,Feed forward
Conference
Volume
ISSN
Citations 
311
1865-0929
0
PageRank 
References 
Authors
0.34
14
1
Name
Order
Citations
PageRank
Pavlo V. Tymoshchuk1152.00