Non-feasible gradient projection recurrent neural network for equality constrained optimization

Barbarosou, M; Maratos, NG

dc.contributor.author	Barbarosou, M	en
dc.contributor.author	Maratos, NG	en
dc.date.accessioned	2014-03-01T02:42:53Z
dc.date.available	2014-03-01T02:42:53Z
dc.date.issued	2004	en
dc.identifier.issn	10987576	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31126
dc.subject	Constrained Optimization	en
dc.subject	Constrained Optimization Problem	en
dc.subject	Convex Optimization	en
dc.subject	Optimization Problem	en
dc.subject	Recurrent Neural Network	en
dc.subject	Satisfiability	en
dc.subject	Neural Network	en
dc.subject.other	Circuit realization	en
dc.subject.other	Constraint gradients	en
dc.subject.other	Equality constrained optimization	en
dc.subject.other	Orthogonal projection	en
dc.subject.other	Constraint theory	en
dc.subject.other	Convergence of numerical methods	en
dc.subject.other	Functions	en
dc.subject.other	Matrix algebra	en
dc.subject.other	Optimization	en
dc.subject.other	Problem solving	en
dc.subject.other	Quadratic programming	en
dc.subject.other	Set theory	en
dc.subject.other	Trajectories	en
dc.subject.other	Recurrent neural networks	en
dc.title	Non-feasible gradient projection recurrent neural network for equality constrained optimization	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/IJCNN.2004.1380972	en
heal.identifier.secondary	http://dx.doi.org/10.1109/IJCNN.2004.1380972	en
heal.publicationDate	2004	en
heal.abstract	A recurrent neural network for equality constrained optimization problems is proposed, which makes use of a cost gradient projection onto the tangent space of the constraints. The proposed neural network constructs a genetically non-feasible trajectory, satisfying the constraints only as t → ∞. Generalized convergence results are given which do not assume convexity of the optimization problems to be solved. Convergence in the usual sense is obtained for convex optimization problems. A circuit realization of the proposed architecture is given to indicate practical implementability of our neural network. Numerical results indicate that the proposed method is efficient and accurate.	en
heal.journalName	IEEE International Conference on Neural Networks - Conference Proceedings	en
dc.identifier.doi	10.1109/IJCNN.2004.1380972	en
dc.identifier.volume	3	en
dc.identifier.spage	2251	en
dc.identifier.epage	2256	en