Kernel Scaling for Manifold Learning and Classification.
Ofir LindenbaumMoshe SalhovArie YeredorAmir AverbuchPublished in: CoRR (2017)
Keyphrases
- manifold learning
- feature space
- dimension reduction
- laplacian eigenmaps
- feature extraction
- dimensionality reduction
- support vector
- semi supervised
- nonlinear dimensionality reduction
- subspace learning
- high dimensional
- low dimensional
- diffusion maps
- feature vectors
- head pose estimation
- high dimensional data
- pattern recognition
- image classification
- kernel function
- sparse representation
- kernel methods
- high dimensionality
- support vector machine svm
- unsupervised learning
- pattern classification
- support vector machine
- dimensionality reduction methods
- feature selection
- model selection
- text classification
- training set
- decision trees
- data sets
- principal component analysis
- kernel matrix
- riemannian manifolds
- preprocessing
- locally linear embedding
- manifold structure
- multiscale
- image processing
- computer vision