ML Anthology

Training Second-Order Recurrent Neural Networks Using Hints

Christian W. Omlin, C. Lee Giles
ICML 1992 pp. 361-366
doi:10.1016/B978-1-55860-247-2.50051-6 /icml/1992/omlin1992icml-training/

Abstract

We investigate a method for inserting rules into discrete-time second-order recurrent neural networks which are trained to recognize regular languages. The rules defining regular languages can be expressed in the form of transitions in the corresponding deterministic finite-state automaton. Inserting these rules as hints into networks with second-order connections is straightforward. Our simulation results show that even weak hints seem to improve the convergence time by an order of magnitude.

ICML Semantic Scholar

Cite

Text

Omlin and Giles. "Training Second-Order Recurrent Neural Networks Using Hints." International Conference on Machine Learning, 1992. doi:10.1016/B978-1-55860-247-2.50051-6

Markdown

[Omlin and Giles. "Training Second-Order Recurrent Neural Networks Using Hints." International Conference on Machine Learning, 1992.](https://mlanthology.org/icml/1992/omlin1992icml-training/) doi:10.1016/B978-1-55860-247-2.50051-6

BibTeX

@inproceedings{omlin1992icml-training,
  title     = {{Training Second-Order Recurrent Neural Networks Using Hints}},
  author    = {Omlin, Christian W. and Giles, C. Lee},
  booktitle = {International Conference on Machine Learning},
  year      = {1992},
  pages     = {361-366},
  doi       = {10.1016/B978-1-55860-247-2.50051-6},
  url       = {https://mlanthology.org/icml/1992/omlin1992icml-training/}
}