liu.seSearch for publications in DiVA
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
The application of an oblique-projected Landweber method to a model of supervised learning
Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för systemteknik, Bildbehandling.
Linköpings universitet, Tekniska högskolan. Linköpings universitet, Matematiska institutionen, Beräkningsvetenskap.
Linköpings universitet, Tekniska högskolan. Linköpings universitet, Matematiska institutionen, Tillämpad matematik.
Department of Mathematics, University of Haifa, Mt. Carmel, Haifa 31905, Israel.
Vise andre og tillknytning
2006 (engelsk)Inngår i: Mathematical and computer modelling, ISSN 0895-7177, E-ISSN 1872-9479, Vol. 43, nr 7-8, s. 892-909Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

This paper brings together a novel information representation model for use in signal processing and computer vision problems, with a particular algorithmic development of the Landweber iterative algorithm. The information representation model allows a representation of multiple values for a variable as well as an expression for confidence. Both properties are important for effective computation using multi-level models, where a choice between models will be implementable as part of the optimization process. It is shown that in this way the algorithm can deal with a class of high-dimensional, sparse, and constrained least-squares problems, which arise in various computer vision learning tasks, such as object recognition and object pose estimation. While the algorithm has been applied to the solution of such problems, it has so far been used heuristically. In this paper we describe the properties and some of the peculiarities of the channel representation and optimization, and put them on firm mathematical ground. We consider the optimization a convexly constrained weighted least-squares problem and propose for its solution a projected Landweber method which employs oblique projections onto the closed convex constraint set. We formulate the problem, present the algorithm and work out its convergence properties, including a rate-of-convergence result. The results are put in perspective with currently available projected Landweber methods. An application to supervised learning is described, and the method is evaluated in an experiment involving function approximation, as well as application to transient signals. © 2006 Elsevier Ltd. All rights reserved.

sted, utgiver, år, opplag, sider
2006. Vol. 43, nr 7-8, s. 892-909
Emneord [en]
Channel representation, Nonnegative constraint, Preconditioner, Projected Landweber, Supervised learning
HSV kategori
Identifikatorer
URN: urn:nbn:se:liu:diva-50254DOI: 10.1016/j.mcm.2005.12.010OAI: oai:DiVA.org:liu-50254DiVA, id: diva2:271150
Tilgjengelig fra: 2009-10-11 Laget: 2009-10-11 Sist oppdatert: 2017-12-12

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekst

Personposter BETA

Johansson, BjörnElfving, TommyKozlov, VladimirForssén, Per-ErikGranlund, Gösta

Søk i DiVA

Av forfatter/redaktør
Johansson, BjörnElfving, TommyKozlov, VladimirForssén, Per-ErikGranlund, Gösta
Av organisasjonen
I samme tidsskrift
Mathematical and computer modelling

Søk utenfor DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 610 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf