Current-Mode Neural Networks For Solving Nonlinear Programming Problems

QSpace/Manakin Repository

Current-Mode Neural Networks For Solving Nonlinear Programming Problems

Show simple item record


dc.contributor.author AI Naima, Fawzi en_US
dc.date.accessioned 2009-11-25T13:04:01Z
dc.date.available 2009-11-25T13:04:01Z
dc.date.issued 2000 en_US
dc.identifier.citation Engineering Journal of Qatar University, 2000, Vol. 13, Pages 223-244. en_US
dc.identifier.uri http://hdl.handle.net/10576/7864
dc.description.abstract In this paper, neural networks for online solution of linear and nonlinear programming problems are presented. Current mode circuits are used in the design of networks. Transimpedance techniques based current conveyors are used for implementing the neurons. Two types of neurons are used in these networks: one being an integrator and the other being used as constraint. Many methods are suggested in this paper to implement networks weights by using current mode circuits such as Operational Transconductance Amplifiers. Network parameters are explicitly computed based upon problem specifications, to cause the network to converge to an equilibrium that represents a solution. Simulation results using Electronic workbench EDA version S.Oa-1996 shows the optimization solutions are obtained almost in real time, acceptable if they are compared with theoretical values, and are stable. en_US
dc.language.iso en en_US
dc.publisher Qatar University en_US
dc.subject Engineering: Electrical Engineering en_US
dc.title Current-Mode Neural Networks For Solving Nonlinear Programming Problems en_US
dc.type Article en_US
dc.identifier.pagination 223-244 en_US
dc.identifier.volume 13 en_US

Files in this item

Files Size Format View
abstract.pdf 2.063Kb PDF View/Open
abstract.doc 20.5Kb Microsoft Word View/Open
06-00-13-0011-fulltext.pdf 628.2Kb PDF View/Open

This item appears in the following Collection(s)

Show simple item record

Search QSpace


Advanced Search

Browse

My Account