Recurrent neural networks with fixed time convergence for linear and quadratic programming

Vista sencilla de ítem
dc.contributor.authorLoukianov, Alexander
dc.contributor.authorSánchez-Torres, Juan D.
dc.contributor.authorSánchez, Edgar
dc.date.accessioned2016-04-19T17:09:55Z
dc.date.available2016-04-19T17:09:55Z
dc.date.issued2013-08-04
dc.descriptionIn this paper, a new class of recurrent neural networks which solve linear and quadratic programs are presented. Their design is considered as a sliding mode control problem, where the network structure is based on the Karush-Kuhn-Tucker (KKT) optimality conditions with the KKT multipliers considered as control inputs to be implemented with fixed time stabilizing terms, instead of common used activation functions. Thus, the main feature of the proposed network is its fixed convergence time to the solution. That means, there is time independent to the initial conditions in which the network converges to the optimization solution. Simulations show the feasibility of the current approach.es
dc.description.sponsorshipConsejo Nacional de Ciencia y Tecnologíaes
dc.identifier.citationJ. D. Sánchez Torres, A. Loukianov, E. Sánchez, “Recurrent neural networks with fixed time convergence for linear and quadratic programming” in International Joint Conference on Neural Networks (IJCNN). Dallas, Texas, 2013.es
dc.identifier.isbn978-1-4673-6128-6
dc.identifier.issn2161-4393
dc.identifier.urihttp://hdl.handle.net/11117/3284
dc.language.isoenges
dc.publisherInstitute of Electrical and Electronics Engineerses
dc.relation.ispartofseries2013 International Joint Conference on Neural Networks (IJCNN);
dc.rights.urihttp://quijote.biblio.iteso.mx/licencias/CC-BY-NC-2.5-MX.pdfes
dc.subjectFixed Time Stabilityes
dc.subjectRecurrent Neural Networkses
dc.subjectLinear Programminges
dc.subjectQuadratic Programminges
dc.titleRecurrent neural networks with fixed time convergence for linear and quadratic programminges
dc.typeinfo:eu-repo/semantics/conferencePaperes
rei.peerreviewedYeses
rei.revisorInternational Joint Conference on Neural Networks (IJCNN)

Archivos

Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
FixedTimeLPQP.pdf
Tamaño:
568.93 KB
Formato:
Adobe Portable Document Format
Descargar

Colecciones

DMAF - Artículos y ponencias con arbitraje