Feature Selection for Unsupervised and Supervised Inference: The Emergence of Sparsity in a Weight-Based Approach.
Lior WolfAmnon ShashuaPublished in: J. Mach. Learn. Res. (2005)
Keyphrases
- feature selection
- unsupervised feature selection
- unsupervised learning
- supervised learning
- semi supervised
- unsupervised methods
- text categorization
- machine learning
- supervised feature selection
- supervised training
- discriminant projection
- bayesian networks
- dimensionality reduction
- supervised and unsupervised learning
- weakly supervised
- feature set
- supervised classification
- probabilistic inference
- semi supervised learning
- selected features
- text classification
- mutual information
- support vector machine
- classification accuracy
- supervised methods
- feature weights
- pointwise mutual information
- information gain
- bayesian inference
- support vector
- document frequency
- inference process
- neural network
- word sense induction
- feature selection algorithms
- feature subset
- probabilistic model
- feature space
- feature weighting
- classification models
- belief networks
- high dimensionality
- sparse representation
- multi class
- irrelevant features
- model selection
- knn
- high dimensional
- learning algorithm