Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/114746
Title: Unsupervised learning by cluster quality optimization
Authors: López-Rubio, Ezequiel
Palomo, Esteban J.
Ortega Zamorano, Francisco 
UNESCO Clasification: 1203 Ciencia de los ordenadores
Keywords: Unsupervised learning
Clustering
Cluster quality measures
K-means
Issue Date: 2018
Journal: Information Sciences 
Abstract: Most clustering algorithms are designed to minimize a distortion measure which quantifies how far the elements of the clusters are from their respective centroids. The assessment of the results is often carried out with the help of cluster quality measures which take into account the compactness and separation of the clusters. However, these measures are not amenable to optimization because they are not differentiable with respect to the centroids even for a given set of clusters. Here we propose a differentiable cluster quality measure, and an associated clustering algorithm to optimize it. It turns out that the standard k-means algorithm is a special case of our method. Experimental results are reported with both synthetic and real datasets, which demonstrate the performance of our approach with respect to several standard quantitative measures.
URI: http://hdl.handle.net/10553/114746
ISSN: 0020-0255
DOI: 10.1016/j.ins.2018.01.007
Source: Information Sciences [ISSN 0020-0255], v. 436-437, p. 31-55, (Abril 2018)
Appears in Collections:Artículos
Show full item record

SCOPUSTM   
Citations

18
checked on May 19, 2024

Page view(s)

80
checked on Apr 27, 2024

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.