randomUniformForest (version 1.0.6)
Random Uniform Forests for Classification and Regression
Description
Ensemble model, for classification and regression, based on a forest of of unpruned and randomized binary trees. Each tree is grown by sampling, with replacement, a set of variables at each node. Each cut-point is generated randomly, according to the Uniform law on the support of each candidate variable. Optimal random node is, then, selected by maximizing information gain (classification) or minimizing 'L2' (or 'L1') distance (regression). Data are either bootstrapped or subsampled for each tree. Random Uniform Forests are aimed to lower correlation between trees, to offer more details about variable importance and selection and to allow native incremental learning.