Weighted Automata Extraction from Recurrent Neural Networks via Regression on State Spaces

04/05/2019

∙

by   Takamasa Okudono, et al.

∙

0

∙

share

We present a method to extract a weighted finite automaton (WFA) from a recurrent neural network (RNN). Our algorithm is based on the WFA learning algorithm by Balle and Mohri, which is in turn an extension of Angluin's classic algorithm. Our technical novelty is in the use of regression methods for the so-called equivalence queries, thus exploiting the internal state space of an RNN. This way we achieve a quantitative extension of the recent work by Weiss, Goldberg and Yahav that extracts DFAs. Experiments demonstrate that our algorithm's practicality.