liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
The application of an oblique-projected Landweber method to a model of supervised learning
Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
Linköping University, The Institute of Technology. Linköping University, Department of Mathematics, Scientific Computing.
Linköping University, The Institute of Technology. Linköping University, Department of Mathematics, Applied Mathematics.
Department of Mathematics, University of Haifa, Mt. Carmel, Haifa 31905, Israel.
Show others and affiliations
2006 (English)In: Mathematical and computer modelling, ISSN 0895-7177, Vol. 43, no 7-8, 892-909 p.Article in journal (Refereed) 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.

Place, publisher, year, edition, pages
2006. Vol. 43, no 7-8, 892-909 p.
Keyword [en]
Channel representation, Nonnegative constraint, Preconditioner, Projected Landweber, Supervised learning
National Category
Engineering and Technology
URN: urn:nbn:se:liu:diva-50254DOI: 10.1016/j.mcm.2005.12.010OAI: diva2:271150
Available from: 2009-10-11 Created: 2009-10-11 Last updated: 2015-12-10

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Johansson, BjörnElfving, TommyKozlov, VladimirForssén, Per-ErikGranlund, Gösta
By organisation
The Institute of TechnologyComputer VisionScientific ComputingApplied Mathematics
In the same journal
Mathematical and computer modelling
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 506 hits
ReferencesLink to record
Permanent link

Direct link