Winner-Relaxing Self-Organizing Maps

dc.creatorClaussen, Jens Christian
dc.date2002-08-21
dc.date2004-11-02
dc.date.accessioned2026-07-07T06:31:50Z
dc.date.available2026-07-07T06:31:50Z
dc.descriptionA new family of self-organizing maps, the Winner-Relaxing Kohonen Algorithm, is introduced as a generalization of a variant given by Kohonen in 1991. The magnification behaviour is calculated analytically. For the original variant a magnification exponent of 4/7 is derived; the generalized version allows to steer the magnification in the wide range from exponent 1/2 to 1 in the one-dimensional case, thus provides optimal mapping in the sense of information theory. The Winner Relaxing Algorithm requires minimal extra computations per learning step and is conveniently easy to implement.
dc.description14 pages (6 figs included). To appear in Neural Computation
dc.identifierhttps://arxiv.org/abs/cond-mat/0208414
dc.identifierhttp://arxiv.org/abs/cond-mat/0208414
dc.identifierNeural Computation 17 (5), 996-1009 (2005)
dc.identifierdoi:10.1162/0899766053491922
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/98726
dc.subjectDisordered Systems and Neural Networks
dc.subjectNeural and Evolutionary Computing
dc.subjectAdaptation and Self-Organizing Systems
dc.subjectNeurons and Cognition
dc.titleWinner-Relaxing Self-Organizing Maps
dc.typetext

Files

Collections