A Feature Selection Approach Based on Information Theory for Classification Tasks.
Jhoseph JesusAnne M. P. CanutoDaniel AraújoPublished in: ICANN (2) (2017)
Keyphrases
- information theory
- feature selection
- information theoretic
- jensen shannon divergence
- mutual information
- statistical learning
- statistical mechanics
- conditional entropy
- text categorization
- feature set
- support vector
- machine learning
- relative entropy
- statistical physics
- feature selection algorithms
- feature space
- feature extraction
- kullback leibler divergence
- naive bayes
- classification accuracy
- learning algorithm
- vector space
- video data
- mdl principle
- dimensionality reduction
- knn
- similarity measure