Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples

Gail Weiss, Yoav Goldberg, Eran Yahav
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:5247-5256, 2018.

Abstract

We present a novel algorithm that uses exact learning and abstraction to extract a deterministic finite automaton describing the state dynamics of a given trained RNN. We do this using Angluin’s \lstar algorithm as a learner and the trained RNN as an oracle. Our technique efficiently extracts accurate automata from trained RNNs, even when the state vectors are large and require fine differentiation.

Cite this Paper


BibTeX
@InProceedings{pmlr-v80-weiss18a, title = {Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples}, author = {Weiss, Gail and Goldberg, Yoav and Yahav, Eran}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {5247--5256}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/weiss18a/weiss18a.pdf}, url = {https://proceedings.mlr.press/v80/weiss18a.html}, abstract = {We present a novel algorithm that uses exact learning and abstraction to extract a deterministic finite automaton describing the state dynamics of a given trained RNN. We do this using Angluin’s \lstar algorithm as a learner and the trained RNN as an oracle. Our technique efficiently extracts accurate automata from trained RNNs, even when the state vectors are large and require fine differentiation.} }
Endnote
%0 Conference Paper %T Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples %A Gail Weiss %A Yoav Goldberg %A Eran Yahav %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-weiss18a %I PMLR %P 5247--5256 %U https://proceedings.mlr.press/v80/weiss18a.html %V 80 %X We present a novel algorithm that uses exact learning and abstraction to extract a deterministic finite automaton describing the state dynamics of a given trained RNN. We do this using Angluin’s \lstar algorithm as a learner and the trained RNN as an oracle. Our technique efficiently extracts accurate automata from trained RNNs, even when the state vectors are large and require fine differentiation.
APA
Weiss, G., Goldberg, Y. & Yahav, E.. (2018). Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:5247-5256 Available from https://proceedings.mlr.press/v80/weiss18a.html.

Related Material