Change search
ReferencesLink to record
Permanent link

Direct link
Activation-based recursive self-organising maps: A general formulation and empirical results
2006 (English)In: Neural Processing Letters, ISSN 1370-4621, E-ISSN 1573-773X, Vol. 24, no 2, 119-136 p.Article in journal (Refereed) Published
Abstract [en]

We generalize a class of neural network models that extend the Kohonen Self-Organising Map (SOM) algorithm into the sequential and temporal domain using recurrent connections. Behaviour of the class of Activation-based Recursive Self-Organising Maps (ARSOM) is discussed with respect to the choice of transfer function and parameter settings. By comparing performances to existing benchmarks we demonstrate the robustness and systematicity of the ARSOM models, thus opening the door to practical applications.

Place, publisher, year, edition, pages
2006. Vol. 24, no 2, 119-136 p.
National Category
Media and Communication Technology
URN: urn:nbn:se:sh:diva-12230DOI: 10.1007/s11063-006-9015-8ISI: 000241220700003OAI: diva2:448588
Available from: 2012-03-21 Created: 2011-10-17 Last updated: 2012-03-21Bibliographically approved

Open Access in DiVA

fulltext(684 kB)83 downloads
File information
File name FULLTEXT03.pdfFile size 684 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Kaipainen, Mauri
In the same journal
Neural Processing Letters
Media and Communication Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 85 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

Altmetric score

Total: 109 hits
ReferencesLink to record
Permanent link

Direct link