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

TL;DR

This paper emphasizes the importance of interpretable AI models in achieving ethical standards and Sustainable Development Goals, proposing methods to extract transparent models from deep learning for sustainable AI development.

Contribution

It introduces approaches to derive truly interpretable models from deep learning, enhancing ethical and sustainable AI practices.

Findings

Interpretable models are crucial for ethical AI and SDGs.

Symbolic models can be extracted from deep learning for transparency.

Proposed methods support sustainable AI development.

Abstract

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.