Constructing deterministic finite-state automata in sparse recurrent neural networks

Christian W. Omlin, C. Lee Giles

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Scopus citations

Abstract

We present an algorithm for encoding deterministic finite-state automata in sparse recurrent neural networks with sigmoidal discriminant functions and second-order weights. We prove that for particular weight strength values the regular languages accepted by DFA's and the constructed networks are identical.

Original languageEnglish (US)
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
PublisherIEEE
Pages1732-1737
Number of pages6
Volume3
StatePublished - 1994
EventProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA
Duration: Jun 27 1994Jun 29 1994

Other

OtherProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
CityOrlando, FL, USA
Period6/27/946/29/94

All Science Journal Classification (ASJC) codes

  • Software

Fingerprint Dive into the research topics of 'Constructing deterministic finite-state automata in sparse recurrent neural networks'. Together they form a unique fingerprint.

Cite this