An Empirical Evaluation of Rule Extraction from Recurrent Neural Networks
This topic contains 0 replies, has 1 voice, and was last updated by arXiv 1 month, 2 weeks ago.

An Empirical Evaluation of Rule Extraction from Recurrent Neural Networks
Rule extraction from blackbox 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, like recurrent neural networks (RNNs), are fit to data. Here, we study the extraction of rules from second order recurrent neural networks (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.
An Empirical Evaluation of Rule Extraction from Recurrent Neural Networks
by Qinglong Wang, Kaixuan Zhang, Alexander G. Ororbia II, Xinyu Xing, Xue Liu, C. Lee Giles
https://arxiv.org/pdf/1709.10380v2.pdf
You must be logged in to reply to this topic.