Rule revision with recurrent neural networks

Christian W. Omlin, C. Lee Giles

Research output: Contribution to journalArticlepeer-review

39 Scopus citations

Abstract

Recurrent neural networks readily process, recognize and generate temporal sequences. By encoding grammatical strings as temporal sequences, recurrent neural networks can be trained to behave like deterministic sequential finite-state automata. Algorithms have been developed for extracting grammatical rules from trained networks. Using a simple method for inserting prior knowledge (or rules) into recurrent neural networks, we show that recurrent neural networks are able to perform rule revision. Rule revision is performed by comparing the inserted rules with the rules in the finite-state automata extracted from trained networks. The results from training a recurrent neural network to recognize a known non-trivial, randomly generated regular grammar show that not only do the networks preserve correct rules but that they are able to correct through training inserted rules which were initially incorrect. (By incorrect, we mean that the rules were not the ones in the randomly generated grammar.).

Original languageEnglish (US)
Pages (from-to)183-188
Number of pages6
JournalIEEE Transactions on Knowledge and Data Engineering
Volume8
Issue number1
DOIs
StatePublished - 1996

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Computer Science Applications
  • Computational Theory and Mathematics

Fingerprint Dive into the research topics of 'Rule revision with recurrent neural networks'. Together they form a unique fingerprint.

Cite this