Interpretable deep-learning models to help achieve the Sustainable Development Goals

Deep-learning models act as black boxes, and lack of interpretability is a challenge. In a recent publication in Nature Machine Intelligence, our colleague Ricardo Vinuesa and his collaborator Beril Sirmacek advocate the use of inherently interpretable models, or frameworks to add interpretability in AI models if we want to achieve the Sustainable Development Goals (SDGs).

Vinuesa, R., Sirmacek, B. Interpretable deep-learning models to help achieve the Sustainable Development Goals. Nat Mach Intell (2021). doi.org/10.1038/s42256-021-00414-y