Fig. 1

Four different ML-pipelines: A unsupervised, B supervised—e.g., humans are providing labels for training data sets and/or select features, C semi-supervised, D shows the iML human-in-the-loop approach: the important issue is that humans are not only involved in pre-processing, by selecting data or features, but actually during the learning phase, directly interacting with the algorithm, thus shifting away the black-box problem to a wished glass-box, 1 input data, 2 pre-processing phase, 3 human agent(s) interacting with the computational agent(s), allowing for crowdsourcing or gamification approaches, 4 final check done by the human expert