Format

Send to

Choose Destination
Neural Netw. 2013 Mar;39:27-39. doi: 10.1016/j.neunet.2012.12.009. Epub 2013 Jan 7.

A class of finite-time dual neural networks for solving quadratic programming problems and its k-winners-take-all application.

Author information

1
Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ 07030, USA. lishuai8@gmail.edu

Abstract

This paper presents a class of recurrent neural networks to solve quadratic programming problems. Different from most existing recurrent neural networks for solving quadratic programming problems, the proposed neural network model converges in finite time and the activation function is not required to be a hard-limiting function for finite convergence time. The stability, finite-time convergence property and the optimality of the proposed neural network for solving the original quadratic programming problem are proven in theory. Extensive simulations are performed to evaluate the performance of the neural network with different parameters. In addition, the proposed neural network is applied to solving the k-winner-take-all (k-WTA) problem. Both theoretical analysis and numerical simulations validate the effectiveness of our method for solving the k-WTA problem.

PMID:
23334164
DOI:
10.1016/j.neunet.2012.12.009
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center