Towards an Axiomatic Approach to "Interpretability"

Peter Bauer, Ulrich Bodenhofer

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

Abstract

The aim of this contribution is to point out the importance of interpretability of fuzzy rule-based systems. We try to approach this key property axiomatically, as a starting point, restricting to interpretability of linguistic variables (in Zadeh's sense). The proposed approach is underlined with an intuitive example. Finally, the benefits of considering interpretability in design and tuning of fuzzy systems are discussed.
Original languageEnglish
Title of host publicationProc. 6th Int. Conf on Soft Computing (IIZUKA2000)
Pages334-339
Number of pages6
Publication statusPublished - Oct 2000

Fields of science

  • 101 Mathematics
  • 101004 Biomathematics
  • 101027 Dynamical systems
  • 101013 Mathematical logic
  • 101028 Mathematical modelling
  • 101014 Numerical mathematics
  • 101020 Technical mathematics
  • 101024 Probability theory
  • 102001 Artificial intelligence
  • 102003 Image processing
  • 102009 Computer simulation
  • 102019 Machine learning
  • 102023 Supercomputing
  • 202027 Mechatronics
  • 206001 Biomedical engineering
  • 206003 Medical physics
  • 102035 Data science

Cite this