Should Machine Learning Models Report to Us When They Are Clueless?. (arXiv:2203.12131v2 [cs.LG] UPDATED)

The right to AI explainability has consolidated as a consensus in the
research community and policy-making. However, a key component of
explainability has been missing: extrapolation, which describes the extent to
which AI models can be clueless when they encounter unfamiliar samples (i.e.,
samples outside the convex hull of their training sets, as we will explain). We
report that AI models extrapolate outside their range of familiar data,
frequently and without notifying the users and stakeholders. Knowing whether a
model …

arxiv learning machine machine learning machine learning models report us