Repositório Institucional da Universidade de Aveiro > Departamento de Electrónica, Telecomunicações e Informática > DETI - Artigos >
 Unsupervised feature extraction via kernel subspace techniques
Please use this identifier to cite or link to this item http://hdl.handle.net/10773/5289

title: Unsupervised feature extraction via kernel subspace techniques
authors: Teixeira, Ana Rita
Tomé, A.M.
Lang, Elmar W.
keywords: Kernel PCA
Feature extractionandlow-rank decompositions
issue date: Feb-2011
publisher: Elsevier
abstract: This paper provides a new insight into unsupervised feature extraction techniques based on kernel subspace models. The data projected onto kernel subspace models are new data representations which might be better suited for classification. The kernel subspace models are always described exploiting the dual form for the basis vectors which requires that the training data must be available even during the test phase. By exploiting an incomplete Cholesky decomposition of the kernel matrix, a computationally less demanding implementation is proposed. Online benchmark data sets allow the evaluation of these feature extraction methods comparing the performance of two classifiers which both have as input either the raw data or the new representations.
URI: http://hdl.handle.net/10773/5289
ISSN: 0925-2312
publisher version/DOI: http://dx.doi.org/10.1016/j.neucom.2010.11.011
source: Neurocomputing
appears in collectionsDETI - Artigos

files in this item

file description sizeformat
neurocompoting2011.pdf551.35 kBAdobe PDFview/open
Restrict Access. You can Request a copy!

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


Valid XHTML 1.0! RCAAP OpenAIRE DeGóis
ria-repositorio@ua.pt - Copyright ©   Universidade de Aveiro - RIA Statistics - Powered by MIT's DSpace software, Version 1.6.2