Representing formal languages: A comparison between finite automata and recurrent neural networks

Joshua J. Michalenko, Ameesh Shah, Abhinav Verma, Richard G. Baraniuk, Swarat Chaudhuri, Ankit B. Patel

    Research output: Contribution to conferencePaperpeer-review

    15 Scopus citations

    Abstract

    We investigate the internal representations that a recurrent neural network (RNN) uses while learning to recognize a regular formal language. Specifically, we train a RNN on positive and negative examples from a regular language, and ask if there is a simple decoding function that maps states of this RNN to states of the minimal deterministic finite automaton (MDFA) for the language. Our experiments show that such a decoding function indeed exists, and that it maps states of the RNN not to MDFA states, but to states of an abstraction obtained by clustering small sets of MDFA states into “superstates”. A qualitative analysis reveals that the abstraction often has a simple interpretation. Overall, the results suggest a strong structural relationship between internal representations used by RNNs and finite automata, and explain the well-known ability of RNNs to recognize formal grammatical structure.

    Original languageEnglish (US)
    StatePublished - 2019
    Event7th International Conference on Learning Representations, ICLR 2019 - New Orleans, United States
    Duration: May 6 2019May 9 2019

    Conference

    Conference7th International Conference on Learning Representations, ICLR 2019
    Country/TerritoryUnited States
    CityNew Orleans
    Period5/6/195/9/19

    All Science Journal Classification (ASJC) codes

    • Education
    • Computer Science Applications
    • Linguistics and Language
    • Language and Linguistics

    Fingerprint

    Dive into the research topics of 'Representing formal languages: A comparison between finite automata and recurrent neural networks'. Together they form a unique fingerprint.

    Cite this