Rule extraction from black box models is critical in domains that require model validation before implementation, as can be the case in credit scoring and medical diagnosis. Though already a challenging problem in statistical learning in general, the difficulty is even greater when highly nonlinear, recursive models, such as recurrent neural networks (RNNs), are fit to data. Here, we study the extraction of rules from second-order RNNs trained to recognize the Tomita grammars. We show that production rules can be stably extracted from trained RNNs and that in certain cases, the rules outperform the trained RNNs.
© 2018 Massachusetts Institute of Technology
Massachusetts Institute of Technology