This paper presents a taxonomy of explainability in human–agent systems. We consider
fundamental questions about the Why, Who, What, When and How of explainability. First, we …

Case-based reasoning (CBR) is an approach to problem solving that emphasizes the role of
prior experience during future problem solving (ie, new problems are solved by reusing and …

Recommender systems try to help users access complex information spaces. A good
example is when they are used to help users to access online product catalogs, where …

Dieses Lehrbuch bietet eine umfassende Einführung in Grundlagen, Potentiale und
Anwendungen Semantischer Technologien. Es richtet sich an Studierende der Infor¬ matik …

Most users of machine-learning products are reluctant to use them without any sense of the
underlying logic that has led to the system's predictions. Unfortunately many of these …

Computer science is on the edge of an important new period of abstraction. A generation
ago we learned to abstract from hardware and currently we are learning to abstract from …

The rapid development of artificial intelligence methods contributes to their wide
applications for forecasting various financial risks in recent years. This study introduces a …

Human-computer trust has shown to be a critical factor in influencing the complexity and
frequency of interaction in technical systems. Particularly incomprehensible situations in …

Traditional explanation strategies in machine learning have been dominated by rule and
decision tree based approaches. Case-based explanations represent an alternative …

Feature Ensembles are a robust and effective method for finding the feature set that yields
the best predictive accuracy for learning agents. However, current feature ensemble …