A global taxonomy of interpretable AI: unifying the terminology for the technical and social sciences.

Since its emergence in the 1960s, Artificial Intelligence (AI) has grown to conquer many technology products and their fields of application. Machine learning, as a major part of the current AI solutions, can learn from the data and through experience to reach high performance on various tasks. This growing success of AI algorithms has led to a need for interpretability to understand opaque models such as deep neural networks. Various requirements have been raised from different domains, together with numerous tools to debug, justify outcomes, and establish the safety, fairness and reliability of the models. This variety of tasks has led to inconsistencies in the terminology with, for instance, terms such as interpretable, explainable and transparent being often used interchangeably in methodology papers. These words, however, convey different meanings and are "weighted" differently across domains, for example in the technical and social sciences. In this paper, we propose an overarching terminology of interpretability of AI systems that can be referred to by the technical developers as much as by the social sciences community to pursue clarity and efficiency in the definition of regulations for ethical and reliable AI development. We show how our taxonomy and definition of interpretable AI differ from the ones in previous research and how they apply with high versatility to several domains and use cases, proposing a-highly needed-standard for the communication among interdisciplinary areas of AI.

Methods for Practising Ethics in Research and Innovation: A Literature Review, Critical Analysis and Recommendations.

This paper provides a systematic literature review, analysis and discussion of methods that are proposed to practise ethics in research and innovation (R&I). Ethical considerations concerning the impacts of R&I are increasingly important, due to the quickening pace of technological innovation and the ubiquitous use of the outcomes of R&I processes in society. For this reason, several methods for practising ethics have been developed in different fields of R&I. The paper first of all presents a systematic search of academic sources that present and discuss such methods. Secondly, it provides a categorisation of these methods according to three main kinds: (1) ex ante methods, dealing with emerging technologies, (2) intra methods, dealing with technology design, and (3) ex post methods, dealing with ethical analysis of existing technologies. Thirdly, it discusses the methods by considering problems in the way they deal with the uncertainty of technological change, ethical technology design, the identification, analysis and resolving of ethical impacts of technologies and stakeholder participation. The results and discussion of our literature review are valuable for gaining an overview of the state of the art and serve as an outline of a future research agenda of methods for practising ethics in R&I.