Reducing High-Dimensional Data by Principal Component Analysis vs. Random Projection for Nearest Neighbor Classification.
Sampath DeegallaHenrik BoströmPublished in: ICMLA (2006)
Keyphrases
- nearest neighbor classification
- high dimensional data
- random projections
- dimensionality reduction
- dimensionality reduction methods
- principal component analysis
- low dimensional
- nearest neighbor
- metric learning
- dimension reduction
- original data
- high dimensionality
- similarity search
- sparse representation
- high dimensional
- lower dimensional
- distance function
- principal components
- linear discriminant analysis
- k nearest neighbor
- data points
- feature space
- data distribution
- distance measure
- preprocessing step
- unsupervised learning
- singular value decomposition
- knn
- feature extraction
- covariance matrix
- euclidean distance
- discriminant analysis
- data analysis
- face recognition
- data mining
- data sets
- principal components analysis
- database
- training set
- pattern recognition
- machine learning