Interpretable deep-learning models to help achieve the Sustainable Development Goals
This work addresses the need for interpretable AI to support ethical and sustainable development, but it appears to be a discussion or review without new experimental results.
The paper discusses the importance of interpretable AI models for ethical AI systems and data-driven solutions aligned with the Sustainable Development Goals (SDGs), highlighting the potential of extracting interpretable models from deep-learning methods, such as through symbolic models with inductive biases.
We discuss our insights into interpretable artificial-intelligence (AI) models, and how they are essential in the context of developing ethical AI systems, as well as data-driven solutions compliant with the Sustainable Development Goals (SDGs). We highlight the potential of extracting truly-interpretable models from deep-learning methods, for instance via symbolic models obtained through inductive biases, to ensure a sustainable development of AI.