Training and retraining of neural network trees

In machine learning, symbolic approaches usually yield comprehensible results without free parameters for further (incremental) retraining. On the other hand, nonsymbolic (connectionist or neural network based) approaches usually yield black-boxes which are difficult to understand and reuse. The goal of this study is to propose a machine learner that is both incrementally retrainable and comprehensible through integration of decision trees and neural networks. In this paper, we introduce a kind of neural network trees (NNTrees), propose algorithms for their training and retraining, and verify the efficiency of the algorithms through experiments with a digit recognition problem.