A neural network for convex optimization

Krasopoulos, PT; Maratos, NG

dc.contributor.author	Krasopoulos, PT	en
dc.contributor.author	Maratos, NG	en
dc.date.accessioned	2014-03-01T02:43:50Z
dc.date.available	2014-03-01T02:43:50Z
dc.date.issued	2006	en
dc.identifier.issn	02714310	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31526
dc.subject	Barrier Function	en
dc.subject	Constrained Optimization Problem	en
dc.subject	Convex Optimization	en
dc.subject	Exact Solution	en
dc.subject	Recurrent Neural Network	en
dc.subject	Interior Point	en
dc.subject	Neural Network	en
dc.subject	Time Varying	en
dc.subject.other	Constrained optimization	en
dc.subject.other	Function evaluation	en
dc.subject.other	Numerical methods	en
dc.subject.other	Parameter estimation	en
dc.subject.other	Problem solving	en
dc.subject.other	Constrained problems	en
dc.subject.other	Convex inequality	en
dc.subject.other	Convex optimization	en
dc.subject.other	Logarithmic barrier functions	en
dc.subject.other	Neural networks	en
dc.title	A neural network for convex optimization	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ISCAS.2006.1692693	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ISCAS.2006.1692693	en
heal.identifier.secondary	1692693	en
heal.publicationDate	2006	en
heal.abstract	A recurrent neural network for convex inequality constrained optimization problems is proposed, based on the logarithmic barrier function with a time varying barrier parameter. Strictly feasible interior point trajectories are created by the network which converge to the exact solution of the constrained problem as t → ∞. A strictly feasible initial point is required; two methods for obtaining such points are presented. Numerical results show that the method is efficient and accurate. © 2006 IEEE.	en
heal.journalName	Proceedings - IEEE International Symposium on Circuits and Systems	en
dc.identifier.doi	10.1109/ISCAS.2006.1692693	en
dc.identifier.spage	747	en
dc.identifier.epage	750	en