Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices.
Sadeep JayasumanaRichard I. HartleyMathieu SalzmannHongdong LiMehrtash Tafazzoli HarandiPublished in: CoRR (2014)
Keyphrases
- kernel methods
- riemannian manifolds
- reproducing kernel hilbert space
- feature space
- euclidean space
- kernel function
- learning problems
- kernel pca
- support vector
- log euclidean
- machine learning
- kernel matrix
- mean shift
- riemannian metric
- vector space
- support vector machine
- multi class classification
- manifold learning
- parameter space
- geodesic distance
- geometric structure
- covariance matrices
- data points
- binary classification
- high dimensional
- covariance matrix
- positive definite
- feature extraction