An Empirical Evaluation of Rule Extraction from Recurrent Neural Networks

By Qinglong Wang, Kaixuan Zhang, Alexander Ororbia, Xinyu Xing, Xue Liu, C. Lee Giles. 2017

66 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning (2019, background): “Most of them are discussed in the surveys [1, 24, 55].”
A comprehensive taxonomy for explainable artificial intelligence: a systematic survey of surveys on methods and concepts (2021, background): “For further rule extraction examples we refer the reader to the comprehensive surveys [60,138,11] on the topic, and the survey [139] for recurrent DNNs.”