Reconstructing signal from fiber-optic measuring system with non-linear perceptron

Simple item page
dc.creatorPanov, A. V.
dc.date2001-03-05
dc.date.accessioned2026-07-07T02:40:38Z
dc.date.available2026-07-07T02:40:38Z
dc.descriptionA computer model of the feed-forward neural network with the hidden layer is developed to reconstruct physical field investigated by the fiber-optic measuring system. The Gaussian distributions of some physical quantity are selected as learning patterns. Neural network is learned by error back-propagation using the conjugate gradient and coordinate descent minimization of deviation. Learned neural network reconstructs the two-dimensional scalar physical field with distribution having one or two Gaussian peaks.
dc.description3 pages, Latex, 1 postscript figure
dc.identifierhttps://arxiv.org/abs/cond-mat/0103092
dc.identifierhttp://arxiv.org/abs/cond-mat/0103092
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/17445
dc.subjectDisordered Systems and Neural Networks
dc.titleReconstructing signal from fiber-optic measuring system with non-linear perceptron
dc.typetext

Files

Collections

arXiv