Enhancing clustering performance of feature maps using randomness

Rasika Amarasiri, Damminda Alahakoon, Malin Premaratne, Kate Smith

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

2 Citations (Scopus)

Abstract

This paper presents an enhancement made to a high dimensional variant of a growing self organizing map called the High Dimensional Growing Self Organizing Map (HDGSOM) that enhances the clustering of the algorithm. The enhancement is based on randomness that expedites the self organizing process by moving the inputs out from local minima producing better clusters within a shorter training time. The enhancement is described in detail and several experiments on very large text datasets illustrating the effect of the enhancement are also presented.

Original languageEnglish
Title of host publicationWSOM 2005 - 5th Workshop on Self-Organizing Maps
Pages463-470
Number of pages8
Publication statusPublished - 2005
Event5th Workshop on Self-Organizing Maps, WSOM 2005 - Paris, France
Duration: 5 Sept 20058 Sept 2005

Conference

Conference5th Workshop on Self-Organizing Maps, WSOM 2005
Country/TerritoryFrance
CityParis
Period5/09/058/09/05

Keywords

  • Growing feature maps
  • GSOM
  • HDGSOM
  • HDGSOMr
  • High dimensions
  • Randomness

Cite this