• Publications
  • Influence
On the Practical Computational Power of Finite Precision RNNs for Language Recognition
While Recurrent Neural Networks (RNNs) are famously known to be Turing complete, this relies on infinite precision in the states and unbounded computation time. We consider the case of RNNs withExpand
  • 93
  • 20
  • PDF
Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples
We address the problem of extracting an automaton from a trained recurrent neural network (RNN). We present a novel algorithm that uses exact learning and abstract interpretation to perform efficientExpand
  • 79
  • 11
  • PDF
A Formal Hierarchy of RNN Architectures
We develop a formal hierarchy of the expressive capacity of RNN architectures. The hierarchy is based on two formal properties: space complexity, which measures the RNN's memory, and rationalExpand
  • 7
  • PDF
Learning Deterministic Weighted Automata with Queries and Counterexamples
We present an algorithm for reconstruction of a probabilistic deterministic finite automaton (PDFA) from a given black-box language model, such as a recurrent neural network (RNN). The algorithm is aExpand
  • 4
  • PDF