Representations Using Partitioning Sample Clauses

Representations Using Partitioning. In Section 2.4 we introduced the simple representation by specifying which atoms can occur. One of the drawbacks of the simple representation is that it creates a possible internal node for each combination of a numerical valued attribute and value that occurs in the data set. In order to reduce the huge number of possible internal nodes that are generated in this way we can use the gain and gain ratio criteria. In C4.5 a single threshold value is selected to split the domain of a numerical valued attribute into two partitions. For our new representations we do something similar. For each numerical valued k−2 attribute Ai with domain Di let Vi = {vi ,..., vi }, with n ≤ k − 1 denote a set of threshold values, where k is the maximum number of partitions. In order to find the optimal set of threshold values we have to look at all possible combinations of at most k − 1 threshold values and compare their gain or gain ratio values so that gain( ratio)[Ai < vi , Ai ∈ [vi , vi ),..., Ai ≥ n |