Proposes a classification schema for AI failures drawn from historical cases to improve incident response and guide risk assessment in development.
An AI designed to do X will eventually fail to do X,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Classification Schemas for Artificial Intelligence Failures
Proposes a classification schema for AI failures drawn from historical cases to improve incident response and guide risk assessment in development.