Anders Uhrenholt

Research Summary

My research centers on machine learning in scenarios where only limited data are available, e.g. patient specific modelling, online experimental design, and user interaction. More broadly, I am interested in problems that require us, as machine learning practioners, to

  1. make the most the available data and computational resources, and
  2. robustly quantify our model accuracy and uncertainty.

The main methodologies in my work are Gaussian processes and Bayesian optimisation.