Optimal pruning of neural tree networks for improved generalization

Abstract

An optimal pruning algorithm for neural tree networks (NTN) is presented. The NTN is grown by a constructive learning algorithm that decreases the classification error on the training data recursively. The optimal pruning algorithm is then used to improve generalization. The pruning algorithm is shown to be computationally inexpensive. Simulation results on a speaker-independent vowel recognition task are presented to show the improved generalization using the pruning algorithm.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>