Many are called, but few are chosen. Feature selection and error estimation in high dimensional spaces.
Helene SchulerudFritz AlbregtsenPublished in: Comput. Methods Programs Biomed. (2004)
Keyphrases
- error estimation
- feature selection
- model selection
- support vector machine
- error estimates
- cross validation
- generalization error
- multi class
- mutual information
- selected features
- feature selection algorithms
- method for feature selection
- bayes classifier
- text categorization
- feature extraction
- support vector
- unsupervised feature selection
- information gain
- feature space
- text classification
- unsupervised learning
- classification accuracy
- active learning
- microarray data
- feature subset
- preprocessing
- discriminative features
- training data
- neural network
- informative features
- objective function
- feature weighting
- high dimensionality
- sample size
- semi supervised