Knowledge extraction from meural networks using the all-Permutations fuzzy rule base: The LED display recognition problem

Eyal Kolman*, Michael Margaliot

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

A major drawback of artificial neural networks (ANNs) is their black-box character. Even when the trained network performs adequately, it is very difficult to understand its operation. In this letter, we use the mathematical equivalence between ANNs and a specific fuzzy rule base to extract the knowledge embedded in the network. We demonstrate this using a benchmark problem: the recognition of digits produced by a light emitting diode (LED) device. The method provides a symbolic and comprehensible description of the knowledge learned by the network during its training.

Original languageEnglish
Pages (from-to)925-931
Number of pages7
JournalIEEE Transactions on Neural Networks
Volume18
Issue number3
DOIs
StatePublished - May 2007

Keywords

  • Feedforward neural networks
  • Hybrid intelligent systems
  • Knowledge extraction
  • Neurofuzzy systems
  • Rule extraction
  • Rule generation

Fingerprint

Dive into the research topics of 'Knowledge extraction from meural networks using the all-Permutations fuzzy rule base: The LED display recognition problem'. Together they form a unique fingerprint.

Cite this