RANDOMFORESTC

Breiman's random forest

    W = RANDOMFORESTC(A,L,N)
    W = A*RANDOMFORESTC([],L,N)

Input
A	Dateset used for training
L	Number of decision trees to be generated (default 200)
N	Size of feature subsets to be used (default 1)

Output
W	Resulting, trained feature space classifier

Description

Train a decision forest on A, using L decision trees, each trained on  a bootstrapped version of dataset A. Each decison tree is using random

feature	subsets of size N in each node. When N=0, no feature subsets
are	used.

The generation of trees might be slow. It might be stopped by PRTIME before L trees are constructed. Set PRTIME larger if desired.

Reference(s)

[1] L. Breiman, Random Forests, Machine learning, vol. 45 (1), 5-32, 2001

See also

datasets, mappings, dtc, prtime,