Within the quantitative data analytics group, we conduct research in the area of machine learning. Hereby, we focus on both fundamental machine learning research and application driven research, the latter primarily applied in the domain of health and wellbeing. We see a strong cross fertilization between the two: applications shed light on fundamental machine learning innovations needed to make them operate in the real world, while fundamental innovations require rigorous testing, also in practical settings. We mainly target approaches that are fueled by structured data (contrary to imaging, text, etc.).
Within the broader area of machine learning, we have six fundamental focal areas:
- Efficiency – how can we make machine learning more data efficient
- Safety – how do we provide safety guarantees for machine learning in critical domains
- Understandability – how can we provide insights into the concepts that have been learned
- Domain knowledge – how can machine learning exploit existing knowledge
- Sequential data – how can we improve machine learning on sequential data and in sequential decision making
- Human and machine – how can machine learning and humans work together in a symbiosis
In the application driven research, personalization in health and wellbeing is one of the main themes as well as predictive modeling for health states.
Click here to go to group's website.