Random Forests with Latent Variables to Foster Feature Selection in the Context of Highly Correlated Variables. Illustration with a Bioinformatics Application.
Christine SinoquetKamel MekhnachaPublished in: IDA (2018)
Keyphrases
- random forests
- latent variables
- highly correlated
- feature selection
- random variables
- random forest
- observed variables
- decision trees
- ensemble methods
- machine learning
- logistic regression
- probabilistic model
- data mining
- topic models
- machine learning algorithms
- multi class
- classification accuracy
- prior knowledge
- information retrieval systems
- high dimensionality
- feature set
- average precision