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

We discuss our insights into interpretable artificial-intelligence (AI)\nmodels, and how they are essential in the context of developing ethical AI\nsystems, as well as data-driven solutions compliant with the Sustainable\nDevelopment Goals (SDGs). We highlight the potential of extracting\ntruly-interpretable models from deep-learning methods, for instance via\nsymbolic models obtained through inductive biases, to ensure a sustainable\ndevelopment of AI.\n