Sparse support vector machines trained in the reduced empirical feature space.
Kazuki IwamuraShigeo AbePublished in: IJCNN (2008)
Keyphrases
- feature space
- support vector
- kernel function
- svm classifier
- high dimensional
- learning machines
- large margin classifiers
- training set
- classification accuracy
- hyperplane
- support vector machine
- kernel methods
- sparse coding
- high dimension
- feature selection
- linear discriminant analysis
- input space
- feature vectors
- reduced set
- support vectors
- low dimensional
- training examples
- cross validation
- sparse data
- generalization ability
- dimension reduction
- high dimensionality
- mercer kernels
- polynomial kernels
- dimensionality reduction
- logistic regression
- data points
- maximum margin
- binary classification
- principal component analysis
- machine learning
- mean shift
- rbf kernel
- feature extraction
- high dimensional feature space
- compressive sensing
- theoretical analysis
- training samples
- multi class
- training stage
- standard svm
- decision trees
- dot product
- learning algorithm
- decision functions
- training process
- input data
- support vector machine svm
- high dimensional data
- eigenvalue decomposition
- radial basis function