Fuzzy knowledge and recurrent neural networks: A dynamical systems perspective

Christian W. Omlin, Lee Giles, K. K. Thornber

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

1 Scopus citations


Hybrid neuro-fuzzy systems - the combination of artificial neural networks with fuzzy logic - are becoming increasingly popular. However, neuro-fuzzy systems need to be extended for applications which require context (e.g., speech, handwriting, control). Some of these appli- cations can be modeled in the form of finite-state automata. This chap- ter presents a synthesis method for mapping fuzzy finite-state automata (FFAs) into recurrent neural networks. The synthesis method requires FFAs to undergo a transformation prior to being mapped into recurrent networks. Their neurons have a slightly enriched functionality in order to accommodate a fuzzy representation of FFA states. This allows fuzzy pa- rameters of FFAs to be directly represented as parameters of the neural network. We present a proof the stability of fuzzy finite-state dynamics of constructed neural networks and through simulations give empirical validation of the proofs.

Original languageEnglish (US)
Title of host publicationHybrid Neural Systems
EditorsStefan Wermter, Ron Sun
PublisherSpringer Verlag
Number of pages21
ISBN (Print)3540673059, 9783540673057
StatePublished - 2000
EventInternational Workshop on Hybrid Neural Systems, 1998 - Denver, United States
Duration: Dec 4 1998Dec 5 1998

Publication series

NameLecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
ISSN (Print)0302-9743


OtherInternational Workshop on Hybrid Neural Systems, 1998
Country/TerritoryUnited States

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • General Computer Science


Dive into the research topics of 'Fuzzy knowledge and recurrent neural networks: A dynamical systems perspective'. Together they form a unique fingerprint.

Cite this