Abstract
Recent success in Artificial Intelligence (AI) and Machine Learning (ML) allow problem solving automatically without any human intervention. Autonomous approaches can be very convenient. However, in certain domains, e.g., in the medical domain, it is necessary to enable a domain expert to understand, why an algorithm came up with a certain result. Consequently, the field of Explainable AI (xAI) rapidly gained interest worldwide in various domains, particularly in medicine. Explainable AI studies transparency and traceability of opaque AI/ML and there are already a huge variety of methods. For example with layer-wise relevance propagation relevant parts of inputs to, and representations in, a neural network which caused a result, can be highlighted. This is a first important step to ensure that end users, e.g., medical professionals, assume responsibility for decision making with AI/ML and of interest to professionals and regulators. Interactive ML adds the component of human expertise to AI/ML processes by enabling them to re-enact and retrace AI/ML results, e.g. let them check it for plausibility. This requires new human–AI interfaces for explainable AI. In order to build effective and efficient interactive human–AI interfaces we have to deal with the question of how to evaluate the quality of explanations given by an explainable AI system. In this paper we introduce our System Causability Scale to measure the quality of explanations. It is based on our notion of Causability (Holzinger et al. in Wiley Interdiscip Rev Data Min Knowl Discov 9(4), 2019) combined with concepts adapted from a widely-accepted usability scale.
Highlights
Artificial intelligence (AI) is an umbrella term for algorithms aiming at delivering task solving capabilities comparable to humans
One currently very successful family of aML methods includes deep learning (DL), which is based on the concepts of neural networks, and the insight that the depth of such networks yields surprising capabilities
Mastering the game of Go has a long tradition and is a good benchmark for progress in automatic approaches, because Go is hard for computers [5] because it is strategic, games are a closed environment with clear rules and a large number of games can be simulated for big data
Summary
Artificial intelligence (AI) is an umbrella term for algorithms aiming at delivering task solving capabilities comparable to humans. Among the most important reasons is trust in the results which is improved by an explanatory interactive learning framework, where the algorithm is able to explain each step to the user and the user can interactively correct the explanation [15]. The advantage of this approach, called interactive machine learning (iML) [16], is to include the strengths of humans, in learning and explaining abstract concepts [17]. Our contribution is to directly measure the user’s perception of an explanation’s utility, including cause aspects, by adapting a well-accepted approach in usability [25]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
