"Why Should I Trust You?"
Marco Túlio RibeiroUniversity of Washington, Seattle, WA, USASameer SinghUniversity of Washington, Seattle, WA, USACarlos GuestrinUniversity of Washington, Seattle, WA, USA
2016en
ABI
Annotatsiya
Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model. Such understanding also provides insights into the model, which can be used to transform an untrustworthy model or prediction into a trustworthy one.
Hali tarjima qilinmagan
Identifikatorlar
Iqtiboslar va manbalar
10 ta iqtibos0 ta foydalanilgan manba