DocumentCode
2745188
Title
A new k-winners-take-all neural network
Author
Liu, Shubao ; Wang, Jun
Author_Institution
Dept. of Autom. & Comput. Eng., Chinese Univ. of Hong Kong, Shatin, China
Volume
2
fYear
2005
fDate
31 July-4 Aug. 2005
Firstpage
712
Abstract
In this paper, the k-winners-take-all (KWTA) operation is converted to an equivalent constrained convex quadratic optimization formulation. A simplified dual neural network, called KWTA network, is further developed for solving the convex quadratic programming (QP) problem. The KWTA network is shown to be globally convergent to the exact optimal solution of the QP problem. Simulation results are presented to show the effectiveness and performance of the KWTA network.
Keywords
convex programming; neural nets; quadratic programming; convex quadratic optimization; convex quadratic programming; k-winners-take-all neural network; Associative memory; Automation; Computer networks; Constraint optimization; Feature extraction; Logic gates; Neural networks; Quadratic programming; Signal processing; Very large scale integration;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on
Print_ISBN
0-7803-9048-2
Type
conf
DOI
10.1109/IJCNN.2005.1555939
Filename
1555939
Link To Document