Higher Order Recurrent Networks and Grammatical Inference

C. Lee Giles, Guo-Zheng Sun, Hsing-Hen Chen, Yee-Chun Lee, Dong Chen

NeurIPS 1989 pp. 380-387

/neurips/1989/giles1989neurips-higher/

Abstract

A higher order single layer recursive network easily learns to simulate a deterministic finite state machine and recognize regular grammars. When an enhanced version of this neural net state machine is connected through a common error term to an external analog stack memory, the combination can be interpreted as a neural net pushdown automata. The neural net finite state machine is given the primitives, push and POP. and is able to read the top of the stack. Through a gradient descent learning rule derived from the common error function, the hybrid network learns to effectively use the stack actions to manipUlate the stack memory and to learn simple context(cid:173) free grammars. INTRODUCTION

PDF NeurIPS Semantic Scholar

Cite

Text

Giles et al. "Higher Order Recurrent Networks and Grammatical Inference." Neural Information Processing Systems, 1989.

Markdown

[Giles et al. "Higher Order Recurrent Networks and Grammatical Inference." Neural Information Processing Systems, 1989.](https://mlanthology.org/neurips/1989/giles1989neurips-higher/)

BibTeX

@inproceedings{giles1989neurips-higher,
  title     = {{Higher Order Recurrent Networks and Grammatical Inference}},
  author    = {Giles, C. Lee and Sun, Guo-Zheng and Chen, Hsing-Hen and Lee, Yee-Chun and Chen, Dong},
  booktitle = {Neural Information Processing Systems},
  year      = {1989},
  pages     = {380-387},
  url       = {https://mlanthology.org/neurips/1989/giles1989neurips-higher/}
}