Dimension reduction for individual ica to decompose FMRI during real-world experiences: principal component analysis vs. canonical correlation analysis.
Valeri TsatsishviliFengyu CongTuomas PuoliväliVinoo AlluriPetri ToiviainenAsoke K. NandiElvira BratticoTapani RistaniemiPublished in: ESANN (2013)
Keyphrases
- dimension reduction
- principal component analysis
- canonical correlation analysis
- partial least squares
- independent component analysis
- dimensionality reduction methods
- real world
- feature extraction
- dimensionality reduction
- linear discriminant analysis
- low dimensional
- face recognition
- general linear model
- principal components
- random projections
- discriminant analysis
- principle component analysis
- feature space
- singular value decomposition
- dimension reduction methods
- variable selection
- manifold learning
- factor analysis
- covariance matrix
- lower dimensional
- preprocessing step
- data analysis
- unsupervised learning
- least squares
- preprocessing
- high dimensional data
- high dimensionality
- data mining
- subspace learning
- high dimensional
- neural network
- cluster analysis
- active learning