A one-layer recurrent neural network for constrained nonconvex optimization

Li, G; Yan, Z; Wang, J

A one-layer recurrent neural network for constrained nonconvex optimization

Li, G Yan, Z

Wang, J

Permalink

Publication Type:: Journal Article
Citation:: Neural Networks, 2015, 61 pp. 10 - 21
Issue Date:: 2015-01-01

Closed Access

	Filename	Description	Size
	1-s2.0-S0893608014002196-main.pdf	Published Version	1.86 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Li, G	en_US
dc.contributor.author	Yan, Z https://orcid.org/0000-0003-3368-2100	en_US
dc.contributor.author	Wang, J	en_US
dc.date.available	2014-09-18	en_US
dc.date.issued	2015-01-01	en_US
dc.identifier.citation	Neural Networks, 2015, 61 pp. 10 - 21	en_US
dc.identifier.issn	0893-6080	en_US
dc.identifier.uri	http://hdl.handle.net/10453/119474
dc.description.abstract	© 2014 Elsevier Ltd. In this paper, a one-layer recurrent neural network is proposed for solving nonconvex optimization problems subject to general inequality constraints, designed based on an exact penalty function method. It is proved herein that any neuron state of the proposed neural network is convergent to the feasible region in finite time and stays there thereafter, provided that the penalty parameter is sufficiently large. The lower bounds of the penalty parameter and convergence time are also estimated. In addition, any neural state of the proposed neural network is convergent to its equilibrium point set which satisfies the Karush-Kuhn-Tucker conditions of the optimization problem. Moreover, the equilibrium point set is equivalent to the optimal solution to the nonconvex optimization problem if the objective function and constraints satisfy given conditions. Four numerical examples are provided to illustrate the performances of the proposed neural network.	en_US
dc.relation.ispartof	Neural Networks	en_US
dc.relation.isbasedon	10.1016/j.neunet.2014.09.009	en_US
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.subject.mesh	Algorithms	en_US
dc.subject.mesh	Neural Networks (Computer)	en_US
dc.subject.mesh	Nonlinear Dynamics	en_US
dc.subject.mesh	Neural Networks, Computer	en_US
dc.title	A one-layer recurrent neural network for constrained nonconvex optimization	en_US
dc.type	Journal Article
utslib.citation.volume	61	en_US
utslib.for	0999 Other Engineering	en_US
utslib.for	0802 Computation Theory and Mathematics	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US
pubs.volume	61	en_US

Abstract:

© 2014 Elsevier Ltd. In this paper, a one-layer recurrent neural network is proposed for solving nonconvex optimization problems subject to general inequality constraints, designed based on an exact penalty function method. It is proved herein that any neuron state of the proposed neural network is convergent to the feasible region in finite time and stays there thereafter, provided that the penalty parameter is sufficiently large. The lower bounds of the penalty parameter and convergence time are also estimated. In addition, any neural state of the proposed neural network is convergent to its equilibrium point set which satisfies the Karush-Kuhn-Tucker conditions of the optimization problem. Moreover, the equilibrium point set is equivalent to the optimal solution to the nonconvex optimization problem if the objective function and constraints satisfy given conditions. Four numerical examples are provided to illustrate the performances of the proposed neural network.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/119474