Feature Selection by Approximating the Markov Blanket in a Kernel-Induced Space.
Qiang LouZoran ObradovicPublished in: ECAI (2010)
Keyphrases
- kernel induced
- feature selection
- markov blanket
- feature space
- text categorization
- variable selection
- feature set
- bayesian networks
- fuzzy c means
- classification accuracy
- structure learning
- text classification
- unsupervised learning
- support vector machine
- euclidean distance
- high dimensionality
- machine learning
- low dimensional
- dimensionality reduction
- support vector
- random projections
- dimension reduction
- feature extraction
- causal discovery
- input space
- fuzzy rules
- graphical models