The group's research interests are in the algorithmic foundations of machine teaching, and applying these algorithms in the application domains of computational education and trustworthy AI. Formally, machine teaching is an inverse problem of machine learning: it involves a teacher with a desired goal, and the teacher's objective is to find an optimal training sequence to steer a student/learner towards this goal. For instance, in an educational setting, the teacher (e.g., a tutoring system) has an educational goal that she wants to communicate to a student via a set of demonstrations; in adversarial attacks known as training-set poisoning, the teacher (e.g., a hacking algorithm) manipulates the behavior of a machine learning system by maliciously modifying the training data. Machine teaching is an emerging sub-field of AI, and the group plans to advance the research on machine teaching via (a) developing new models, algorithms, and theory of machine teaching; (b) applying these algorithms to real-world applications by building and deploying new services. The following two websites serve as good starting points to get more familiar with the above-mentioned research interests: (i) and (ii)


Imprint / Data Protection