Challenges of Explaining the Behavior of Black-Box AI Systems
Research output: Journal Article or Conference Article in Journal › Journal article › Research › peer-review
There are many examples of problems resulting from inscrutable AI systems, so there is a growing need to be able to explain how such systems produce their outputs. Draw- ing on a case study at the Danish Business Authority, we provide a framework and recommendations for addressing the many challenges of explaining the behavior of black-box AI systems. Our findings will enable organizations to successfully develop and deploy AI systems without causing legal or ethical problems.
|Journal||M I S Quarterly Executive|
|Publication status||Published - 1 Dec 2020|
No data available