Title :
A K-Winners-Take-All Neural Network Based on Linear Programming Formulation
Author :
Gu, Shenshen ; Wang, Jun
Author_Institution :
Chinese Univ. of Hong Kong, Hong Kong
Abstract :
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.
Keywords :
linear programming; recurrent neural nets; k-winners-take-all neural network; linear programming; recurrent neural network; Associative memory; Computer networks; Electrical capacitance tomography; Feature extraction; Linear programming; Neural networks; Recurrent neural networks; Signal processing; Vectors; Very large scale integration;
Conference_Titel :
Neural Networks, 2007. IJCNN 2007. International Joint Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
978-1-4244-1379-9
Electronic_ISBN :
1098-7576
DOI :
10.1109/IJCNN.2007.4370927
