Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples

Gail Weiss; Yoav Goldberg; Eran Yahav

Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples

Gail Weiss
, Yoav Goldberg
, Eran Yahav

Department of Computer Science

Technion-Israel Institute of Technology

Research output: Contribution to journal › Conference article › peer-review

72 Scopus citations

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 L^∗ 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.

Original language	English
Pages (from-to)	5247-5256
Number of pages	10
Journal	Proceedings of Machine Learning Research
Volume	80
State	Published - 2018
Event	35th International Conference on Machine Learning, ICML 2018 - Stockholm, Sweden Duration: 10 Jul 2018 → 15 Jul 2018

Bibliographical note

Publisher Copyright:
© 2018 by the author(s).

Cite this

@article{426504bbe5da443f8e6dd9a1806021e9,

title = "Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples",

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{\textquoteright}s L∗ 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.",

author = "Gail Weiss and Yoav Goldberg and Eran Yahav",

note = "Publisher Copyright: {\textcopyright} 2018 by the author(s).; 35th International Conference on Machine Learning, ICML 2018 ; Conference date: 10-07-2018 Through 15-07-2018",

year = "2018",

language = "אנגלית",

volume = "80",

pages = "5247--5256",

journal = "Proceedings of Machine Learning Research",

issn = "2640-3498",

publisher = "ML Research Press",

}

TY - JOUR

T1 - Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples

AU - Weiss, Gail

AU - Goldberg, Yoav

AU - Yahav, Eran

PY - 2018

Y1 - 2018

N2 - 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 L∗ 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.

AB - 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 L∗ 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.

UR - https://www.scopus.com/pages/publications/105020573253

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.conferencearticle???

AN - SCOPUS:105020573253

SN - 2640-3498

VL - 80

SP - 5247

EP - 5256

JO - Proceedings of Machine Learning Research

JF - Proceedings of Machine Learning Research

T2 - 35th International Conference on Machine Learning, ICML 2018

Y2 - 10 July 2018 through 15 July 2018

ER -

Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples

Abstract

Bibliographical note

Other files and links

Fingerprint

Cite this