Context (archaeology)

Engineering

Ecology

Biology

Archaeology

Computer science

Risk analysis (engineering)

Management science

Business

Process management

Development (topology)

Mathematics

Geography

Political science

Environmental resource management

Sustainable development

Environmental science

Mathematical analysis

Data science

Artificial intelligence

Deep learning

Knowledge management

Machine learning

Nature Machine Intelligence

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.

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