Using the oob error rate (see below) a value of m in the range can quickly be found. Somewhere in between is an "optimal" range of m - usually quite wide. Reducing m reduces both the correlation and the strength. Increasing the strength of the individual trees decreases the forest error rate. A tree with a low error rate is a strong classifier. The strength of each individual tree in the forest.Increasing the correlation increases the forest error rate. The correlation between any two trees in the forest.In the original paper on random forests, it was shown that the forest error rate depends on two things: Each tree is grown to the largest extent possible.The value of m is held constant during the forest growing. If there are M input variables, a number mThis sample will be the training set for growing the tree. If the number of cases in the training set is N, sample N cases at random - but with replacement, from the original data.The forest chooses the classification having the most votes (over all the trees in the forest). Each tree gives a classification, and we say the tree "votes" for that class. To classify a new object from an input vector, put the input vector down each of the trees in the forest. Random Forests grows many classification trees. We assume that the user knows about the construction of single classification trees. This section gives a brief overview of random forests and some comments about the features of the method.
0 kommentar(er)
