A performance comparison of trained multilayer perceptrons and trained classification trees

Multilayer Perceptrons and trained classification trees are two very different techniques which have recently become popular. Given enough data and time, both methods are capable of performing arbitrary nonlinear classification. We first consider the important differences between multilayer Perceptrons and classification trees and conclude that there is not enough theoretical basis for the clear-cut superiority of one technique over the other. For this reason, we performed a number of empirical tests on three real-world problems in power system load forecasting, power system security prediction, and speaker-independent vowel recognition. In all cases, even for piecewise-linear trees, the multilayer Perceptron performed as well as or better than the trained classification trees.