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

Direct link
On Sparse Associative Networks: A Least Squares Formulation
Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.
2001 (English)Report (Other academic)
Abstract [en]

This report is a complement to the working document [1], where a sparse associative network is described. This report shows that the net learning rule in [1] can be viewed as the solution to a weighted least squares problem. This means that we can apply the theory framework of least squares problems, and compare the net rule with some other iterative algorithms that solve the same problem. The learning rule is compared with the gradient search algorithm and the RPROP algorithm in a simple synthetic experiment. The gradient rule has the slowest convergence while the associative and the RPROP rules have similar convergence. The associative learning rule has a smaller initial error than the RPROP rule though.

It is also shown in the same experiment that we get a faster convergence if we have a monopolar constraint on the solution, i.e. if the solution is constrained to be non-negative. The least squares error is a bit higher but the norm of the solution is smaller, which gives a smaller interpolation error.

The report also discusses a generalization of the least squares model, which include other known function approximation models.

[1] G Granlund. Paralell Learning in Artificial Vision Systems: Working Document. Dept. EE, Linköping University, 2000

Place, publisher, year, edition, pages
2001. , 23 p.
LiTH-ISY-R, ISSN 1400-3902 ; 2368
Keyword [en]
Least squares model
National Category
Engineering and Technology
URN: urn:nbn:se:liu:diva-36329ISRN: LiTH-ISY-R-2368Local ID: 30987OAI: diva2:257177
Available from: 2009-10-10 Created: 2009-10-10 Last updated: 2014-08-28Bibliographically approved

Open Access in DiVA

fulltext(1407 kB)71 downloads
File information
File name FULLTEXT01.pdfFile size 1407 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Johansson, Björn
By organisation
The Institute of TechnologyComputer Vision
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 71 downloads
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

Total: 114 hits
ReferencesLink to record
Permanent link

Direct link