Out-of-sample kernel extensions for nonparametric dimensionality reduction.
Andrej GisbrechtWouter LueksBassam MokbelBarbara HammerPublished in: ESANN (2012)
Keyphrases
- dimensionality reduction
- kernel pca
- kernel learning
- feature space
- kernel density estimation
- input space
- class separability
- kernel trick
- kernel discriminant analysis
- graph kernels
- principal component analysis
- high dimensional data
- kernel methods
- nadaraya watson
- data representation
- kernel regression
- high dimensional
- high dimensionality
- kernel function
- kernel density
- kernel density estimator
- low dimensional
- parzen window
- feature extraction
- data driven
- linear dimensionality reduction
- dimensionality reduction methods
- structure preserving
- pattern recognition and machine learning
- linear discriminant analysis
- pattern recognition
- mean shift
- data points
- random projections
- component analysis
- graph embedding
- multiple kernel learning
- density estimation
- feature selection
- support vector
- image processing
- computer vision
- manifold learning
- nonparametric regression
- principal components
- least squares
- nonlinear dimensionality reduction
- lower dimensional
- nonparametric density estimation