ML Anthology

Induction of Finite-State Languages Using Second-Order Recurrent Networks

Raymond L. Watrous, Gary M. Kuhn
NeCo 1992 pp. 406-414
doi:10.1162/NECO.1992.4.3.406 /neco/1992/watrous1992neco-induction/

Abstract

Second-order recurrent networks that recognize simple finite state languages over 0,1* are induced from positive and negative examples. Using the complete gradient of the recurrent network and sufficient training examples to constrain the definition of the language to be induced, solutions are obtained that correctly recognize strings of arbitrary length.

NeCo Semantic Scholar

Cite

Text

Watrous and Kuhn. "Induction of Finite-State Languages Using Second-Order Recurrent Networks." Neural Computation, 1992. doi:10.1162/NECO.1992.4.3.406

Markdown

[Watrous and Kuhn. "Induction of Finite-State Languages Using Second-Order Recurrent Networks." Neural Computation, 1992.](https://mlanthology.org/neco/1992/watrous1992neco-induction/) doi:10.1162/NECO.1992.4.3.406

BibTeX

@article{watrous1992neco-induction,
  title     = {{Induction of Finite-State Languages Using Second-Order Recurrent Networks}},
  author    = {Watrous, Raymond L. and Kuhn, Gary M.},
  journal   = {Neural Computation},
  year      = {1992},
  pages     = {406-414},
  doi       = {10.1162/NECO.1992.4.3.406},
  volume    = {4},
  url       = {https://mlanthology.org/neco/1992/watrous1992neco-induction/}
}