Designing Machine-In-The-Loop Systems to Transfer Knowledge

  • Background

    With the rise of machine learning (ML) in various industry domains, applications utilizing ML become more prevalent. One reason for their capability to achieve promising performances is the fact that these systems are trained on data provided by domain experts – and hence incorporate expert knowledge. At the same time, ML systems can also be used to teach inexperienced humans on particular tasks (machine teaching) [1] and thereby externalize their knowledge.

    With the call in research to examine how these ML systems can be utilized as knowledge transfer systems it is crucial to comprehend and outline a design of such machine-in-the-loop systems.


    Research Goal

    While human-in-the-loop (HITL) systems as paradigm to have human an AI collaborate on specific tasks are extensively analyzed by scholars [2], in this master’s thesis you will apply and extend your know-how in the interface of machine learning and machine teaching. In this, you will scrutinize how to develop and design machine-in-the-loop (MITL) systems for machine teaching applications with the aid of prevalent research methodologies like Design Science Research[3].


    Working on this thesis you will:

    - Apply your theoretical machine learning know-how to relevant articles in the domain of knowledge-driven ML-systems
    - Develop an artifact for the design of machine-in-the-loop systems for machine teaching scenarios
    - Become an expert in machine learning and machine teaching


    We look forward to receiving your application because you:

    - You are interested in the field of machine learning
    - You are highly motivated to work on recent real-world problems in a self-organized and goal-oriented working mode and you bring in own ideas
    - You are open-minded and don’t hesitate to get in touch with professionals, e.g., throughout an interview study
    - Very good English skills as the thesis will be written in English



     - Start: immediately 

     - Duration: 6 months

     - Location: up to you

    We offer you a challenging research topic, close supervision, and the opportunity to develop practical and theoretical skills. If you are interested, send your CV, transcript of records, and a brief letter of motivation to


    [1] Goyal, Y., Wu, Z., Ernst, J., Batra, D., Parikh, D., & Lee, S. (2019, May). Counterfactual visual explanations. In International Conference on Machine Learning (pp. 2376-2384). PMLR.
    [2] Zanzotto, F. M. (2019). Human-in-the-loop artificial intelligence. Journal of Artificial Intelligence Research, 64, 243-252.
    [3] Gregor, S., & Hevner, A. R. (2013). Positioning and presenting design science research for maximum impact. MIS quarterly, 337-355.