Dimensionality Reduction of High-Dimensional Data with a NonLinear Principal Component Aligned Generative Topographic Mapping.
Michael GriebelAlexander HullmannPublished in: SIAM J. Sci. Comput. (2014)
Keyphrases
- principal components
- dimensionality reduction
- high dimensional data
- generative topographic mapping
- low dimensional
- dimension reduction
- manifold learning
- principal component analysis
- high dimensionality
- high dimensional
- subspace clustering
- input space
- linear discriminant analysis
- feature extraction
- principal components analysis
- original data
- similarity search
- underlying manifold
- feature space
- nonlinear dimensionality reduction
- pattern recognition
- data points
- unsupervised learning
- sparse representation
- variable selection
- high dimensional spaces
- feature selection
- singular value decomposition
- self organizing maps
- euclidean distance
- locally linear embedding
- machine learning
- neural network
- hyperplane
- nearest neighbor
- data mining
- data clustering
- euclidean space
- vector space
- data sets
- semi supervised
- real world