DocumentCode
2952067
Title
Classification constrained dimensionality reduction
Author
Costa, Jose A. ; Hero, Alfred O., III
Author_Institution
Dept. of Electr. Eng. & Comput. Sci., Michigan Univ., Ann Arbor, MI, USA
Volume
5
fYear
2005
fDate
18-23 March 2005
Abstract
In this paper, we propose a nonlinear dimensionality reduction method aimed at extracting lower-dimensional features relevant for classification tasks. This is obtained by modifying the Laplacian approach to manifold learning through the introduction of class dependent constraints. Using synthetic data sets, we show that the proposed algorithm can greatly improve both supervised and semi-supervised learning problems.
Keywords
computational geometry; feature extraction; learning (artificial intelligence); signal classification; Laplacian manifold learning; class dependent constraints; classification constrained dimensionality reduction; lower-dimensional feature extraction; nonlinear dimensionality reduction; semi-supervised learning; supervised learning; Data mining; Feature extraction; Laplace equations; Machine learning; Machine learning algorithms; Manifolds; Sampling methods; Semisupervised learning; Signal processing algorithms; Symmetric matrices;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on
ISSN
1520-6149
Print_ISBN
0-7803-8874-7
Type
conf
DOI
10.1109/ICASSP.2005.1416494
Filename
1416494
Link To Document