Article published in IEEE Software Journal

The teams from Fraunhofer Institute and University of Hull had an article appear in the IEEE Software journal. The article titled: Explaining Black Boxes With a SMILE: Statistical Model-Agnostic Interpretability With Local Explanations addresses trustworthiness as one of the major barriers to widespread acceptance of machine learning (ML). Most ML models operate as black boxes, their inner workings opaque and mysterious, and can be difficult to trust their conclusions without understanding how those conclusions are reached. The article proposes the SMILE tool from the SESAME Project as a new method that builds on previous approaches by making use of statistical distance measures to improve explainability while remaining applicable to a wide range of input data domains.