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, non-symbolic (connectionist or neural network based) approaches usually yield black-boxes which are diicult 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 eeciency of the algorithms through experiments with a digit recognition problem.