Derck Prinzhorn

I am a MSc Artificial Intelligence student at the University of Amsterdam (UvA) and a Machine Learning Architect at the Dutch Police.

Last year, I have focused on doing research internships and now I'm exploring the start-up world. Recently, I started my own company called Wisr, an education technology start-up focused on empowering teachers and students.

My interests are broad, but I tend to focus on high-risk AI applications. This includes topics such as responsible AI, AI safety, conformal prediction, medical AI, and AI for education.

In 2020 I started my Bachelor's in AI at the UvA. Next to studying, I worked as a Teaching Assistant at the UvA, as a software engineer at LeerLevels and became active in our robotics student team: Dutch Nao Team. My bachelor thesis was about uncertainty quantification in which I benchmarked various adaptive conformal prediction methods for time series.

Email  |  GitHub  |  Google Scholar  |  LinkedIn  |  CV

Highlights / News

Research

I'm interested in AI safety, conformal prediction, medical AI and edtech.

Conformal time series decomposition with component-wise exchangeability

We present a novel use of conformal prediction for time series forecasting that incorporates time series decomposition.

Reproducibility study of FairAC

This work reproduces Guo et al. (2023) on “Fair Attribute Completion on Graph with Missing Attributes,” confirming its claims, generalizability, and fairness improvements, with a refactored codebase.

Design and source code from Jon Barron's website