Explainable Artificial Intelligence: Concepts, Applications, Research Challenges and Visions

Abstract

The development of theory, frameworks and tools for Explainable AI (XAI) is a very active area of research these days, and articulating any kind of coherence on a vision and challenges is itself a challenge. At least two sometimes complementary and colliding threads have emerged. The first focuses on the development of pragmatic tools for increasing the transparency of automatically learned prediction models, as for instance by deep or reinforcement learning. The second is aimed at anticipating the negative impact of opaque models with the desire to regulate or control impactful consequences of incorrect predictions, especially in sensitive areas like medicine and law. The formulation of methods to augment the construction of predictive models with domain knowledge can provide support for producing human understandable explanations for predictions. This runs in parallel with AI regulatory concerns, like the European Union General Data Protection Regulation, which sets standards for the production of explanations from automated or semi-automated decision making. Despite the fact that all this research activity is the growing acknowledgement that the topic of explainability is essential, it is important to recall that it is also among the oldest fields of computer science. In fact, early AI was re-traceable, interpretable, thus understandable by and explainable to humans. The goal of this research is to articulate the big picture ideas and their role in advancing the development of XAI systems, to acknowledge their historical roots, and to emphasise the biggest challenges to moving forward.