A mental models approach for defining explainable artificial intelligence.

Journal: BMC medical informatics and decision making
PMID:

Abstract

BACKGROUND: Wide-ranging concerns exist regarding the use of black-box modelling methods in sensitive contexts such as healthcare. Despite performance gains and hype, uptake of artificial intelligence (AI) is hindered by these concerns. Explainable AI is thought to help alleviate these concerns. However, existing definitions for explainable are not forming a solid foundation for this work.

Authors

  • Michael Merry
    School of Computer Science, University of Auckland, Symonds St, Auckland, New Zealand. m.merry@auckland.ac.nz.
  • Pat Riddle
    School of Computer Science, University of Auckland, Symonds St, Auckland, New Zealand.
  • Jim Warren
    University of Auckland, New Zealand.