Generating Neural Networks Through the Induction of Threshold Logic Unit Trees (Extended Abstract

Abstract. We investigate the generation of neural networks through the induction of binary trees of threshold logic units (TLUs). Initially, we describe the framework for our tree construction algorithm and how such trees can be transformed into an isomorphic neural network topology. Several methods for learning the linear discriminant functions at each node of the tree structure are examined and shown to produce accuracy results that are comparable to classical information theoretic methods for constructing decision trees (which use single feature tests at each node). Our TLU trees, however, are smaller and thus easier to understand. Moreover, we show that it is possible to simultaneously learn both the topology and weight settings of a neural network simply using the training data set that we are given.