Using conditional bias in principal component analysis for the evaluation of joint influence on the eigenvalues of the covariance matrix.
Alicia Enguix-GonzálezJ. M. Muñoz-PichardoJ. L. Moreno-RebolloI. Barranco-ChamorroPublished in: Appl. Math. Comput. (2012)
Keyphrases
- covariance matrix
- principal component analysis
- covariance matrices
- sample size
- correlation matrix
- mahalanobis distance
- eigenvalues and eigenvectors
- geometrical interpretation
- principal components
- pseudo inverse
- multivariate gaussian
- dimensionality reduction
- eigendecomposition
- gaussian mixture
- face recognition
- positive definite
- feature extraction
- independent component analysis
- low dimensional
- special case
- graph representation
- mixture model
- particle swarm optimization
- feature space
- objective function
- cma es