Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples – ICML 2018

On the Practical Computational Power of Finite Precision RNNs for Language Recognition – ACL 2018

  • Gail Weiss, Yoav Goldberg, Eran Yahav
  • PDF
  • Short Talk (ACL ’18)
  • Github Repository (this paper is mostly an observation that LSTMs can implement a counting mechanism and GRUs can’t, so this code is just a demonstration of this. You can download it and run the demonstration yourself, or just open the google colab notebook)
  • Google Colaboratory (looks messy, but press “open with colaboratory” and it sorts itself out)

Learning Deterministic Weighted Automata with Queries and Counterexamples – NeurIPS 2019