“Why Should I Trust You?” Explaining the Predictions of ...

Why Should I Trust You? Explaining the Predictions of Any ClassifierMarco Tulio RibeiroUniversity of WashingtonSeattle, WA 98105, SinghUniversity of WashingtonSeattle, WA 98105, GuestrinUniversity of WashingtonSeattle, WA 98105, widespread adoption, machine learning models re-main mostly black boxes. Understanding the reasons behindpredictions is, however, quite important in assessingtrust,which is fundamental if one plans to take action based on aprediction, or when choosing whether to deploy a new understanding also provides insights into the model,which can be used to transform an untrustworthy model orprediction into a trustworthy this work, we propose LIME, a novel explanation tech-nique that explains the Predictions ofanyclassifier in an in-terpretable and faithful manner, by learning an interpretablemodel locall

Despite widespread adoption, machine learning models re-main 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 ...

Tags:

  Trust, Explaining, Prediction, Trust you, Explaining the predictions of

Information

Related search queries