Automatically finding clusters in normalized cuts

Normalized Cuts is a state-of-the-art spectral method for clustering. By applying spectral techniques, the data becomes easier to cluster and then k-means is classically used. Unfortunately the number of clusters must be manually set and it is very sensitive to initialization. Moreover, k-means tend...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Tepper, Mariano Hernán, Mejail, Marta Estela
Publicado:	2011
Materias:	A contrario detection Clustering Normalized cuts Clustering methods Data dimensionality K-means Large clusters Number of clusters Small clusters Spectral methods Spectral techniques Spectroscopy
Acceso en línea:	https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_00313203_v44_n7_p1372_Tepper http://hdl.handle.net/20.500.12110/paper_00313203_v44_n7_p1372_Tepper
Aporte de:	Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires

id	paper:paper_00313203_v44_n7_p1372_Tepper
record_format	dspace
spelling	paper:paper_00313203_v44_n7_p1372_Tepper2023-06-08T14:57:00Z Automatically finding clusters in normalized cuts Tepper, Mariano Hernán Mejail, Marta Estela A contrario detection Clustering Normalized cuts A contrario detection Clustering Clustering methods Data dimensionality K-means Large clusters Normalized cuts Number of clusters Small clusters Spectral methods Spectral techniques Spectroscopy Normalized Cuts is a state-of-the-art spectral method for clustering. By applying spectral techniques, the data becomes easier to cluster and then k-means is classically used. Unfortunately the number of clusters must be manually set and it is very sensitive to initialization. Moreover, k-means tends to split large clusters, to merge small clusters, and to favor convex-shaped clusters. In this work we present a new clustering method which is parameterless, independent from the original data dimensionality and from the shape of the clusters. It only takes into account inter-point distances and it has no random steps. The combination of the proposed method with normalized cuts proved successful in our experiments. © 2011 Elsevier Ltd. All rights reserved. Fil:Tepper, M. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. Fil:Mejail, M. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. 2011 https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_00313203_v44_n7_p1372_Tepper http://hdl.handle.net/20.500.12110/paper_00313203_v44_n7_p1372_Tepper
institution	Universidad de Buenos Aires
institution_str	I-28
repository_str	R-134
collection	Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA)
topic	A contrario detection Clustering Normalized cuts A contrario detection Clustering Clustering methods Data dimensionality K-means Large clusters Normalized cuts Number of clusters Small clusters Spectral methods Spectral techniques Spectroscopy
spellingShingle	A contrario detection Clustering Normalized cuts A contrario detection Clustering Clustering methods Data dimensionality K-means Large clusters Normalized cuts Number of clusters Small clusters Spectral methods Spectral techniques Spectroscopy Tepper, Mariano Hernán Mejail, Marta Estela Automatically finding clusters in normalized cuts
topic_facet	A contrario detection Clustering Normalized cuts A contrario detection Clustering Clustering methods Data dimensionality K-means Large clusters Normalized cuts Number of clusters Small clusters Spectral methods Spectral techniques Spectroscopy
description	Normalized Cuts is a state-of-the-art spectral method for clustering. By applying spectral techniques, the data becomes easier to cluster and then k-means is classically used. Unfortunately the number of clusters must be manually set and it is very sensitive to initialization. Moreover, k-means tends to split large clusters, to merge small clusters, and to favor convex-shaped clusters. In this work we present a new clustering method which is parameterless, independent from the original data dimensionality and from the shape of the clusters. It only takes into account inter-point distances and it has no random steps. The combination of the proposed method with normalized cuts proved successful in our experiments. © 2011 Elsevier Ltd. All rights reserved.
author	Tepper, Mariano Hernán Mejail, Marta Estela
author_facet	Tepper, Mariano Hernán Mejail, Marta Estela
author_sort	Tepper, Mariano Hernán
title	Automatically finding clusters in normalized cuts
title_short	Automatically finding clusters in normalized cuts
title_full	Automatically finding clusters in normalized cuts
title_fullStr	Automatically finding clusters in normalized cuts
title_full_unstemmed	Automatically finding clusters in normalized cuts
title_sort	automatically finding clusters in normalized cuts
publishDate	2011
url	https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_00313203_v44_n7_p1372_Tepper http://hdl.handle.net/20.500.12110/paper_00313203_v44_n7_p1372_Tepper
work_keys_str_mv	AT teppermarianohernan automaticallyfindingclustersinnormalizedcuts AT mejailmartaestela automaticallyfindingclustersinnormalizedcuts
_version_	1768543123922747392

Automatically finding clusters in normalized cuts

Ejemplares similares