TY - GEN
T1 - A K-winners-take-all neural network based on linear programming formulation
AU - Gu, Shenshen
AU - Wang, Jun
PY - 2007
Y1 - 2007
N2 - In this paper, the K-Winners-Take-All (KWTA) problem is formulated equivalently to a linear program. A recurrent neural network for KWTA is then proposed for solving the linear programming problem. The KWTA network is globally convergent to the optimal solution of the KWTA problem. Simulation results are further presented to show the effectiveness and performance of the KWTA network. ©2007 IEEE.
AB - In this paper, the K-Winners-Take-All (KWTA) problem is formulated equivalently to a linear program. A recurrent neural network for KWTA is then proposed for solving the linear programming problem. The KWTA network is globally convergent to the optimal solution of the KWTA problem. Simulation results are further presented to show the effectiveness and performance of the KWTA network. ©2007 IEEE.
UR - http://www.scopus.com/inward/record.url?scp=51749114664&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-51749114664&origin=recordpage
U2 - 10.1109/IJCNN.2007.4370927
DO - 10.1109/IJCNN.2007.4370927
M3 - RGC 32 - Refereed conference paper (with host publication)
SN - 142441380
SN - 9781424413805
SP - 37
EP - 40
BT - IEEE International Conference on Neural Networks - Conference Proceedings
T2 - 2007 International Joint Conference on Neural Networks, IJCNN 2007
Y2 - 12 August 2007 through 17 August 2007
ER -