Neural networks=Fuzzy rule bases

Eyal Kolman*, Michael Margaliot

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

We introduce a novel Mamdani-type fuzzy model, referred to as the allpermutations fuzzy rule-base (APFRB). We show that any standard feedforward neural network is mathematically equivalent to an appropriate APFRB. This implies that we can easily extract the knowledge embedded in a trained neural network in the form of fuzzy rules.

Original languageEnglish
Title of host publicationApplied Computational Intelligence - Proceedings of the 6th International FLINS Conference
PublisherWorld Scientific Publishing Co. Pte Ltd
Pages111-117
Number of pages7
ISBN (Print)9812388737, 9789812388735
DOIs
StatePublished - 2004
EventApplied Computational Intelligence - Proceedings of the 6th International FLINS Conference - Blankenberge, Belgium
Duration: 1 Sep 20043 Sep 2004

Publication series

NameApplied Computational Intelligence - Proceedings of the 6th International FLINS Conference

Conference

ConferenceApplied Computational Intelligence - Proceedings of the 6th International FLINS Conference
Country/TerritoryBelgium
CityBlankenberge
Period1/09/043/09/04

Fingerprint

Dive into the research topics of 'Neural networks=Fuzzy rule bases'. Together they form a unique fingerprint.

Cite this