Chair of Artificial Intelligence and Machine Learning
print
Breadcrumb Navigation
Content
Patrick Kolpaczki

Patrick Kolpaczki, M.Sc.

PhD student (Paderborn University)

Contact

Ludwig-Maximilians-Universität München
Institute of Informatics
Chair of Artificial Intelligence and Machine Learning
Prof. Dr. Eyke Hüllermeier
Akademiestr.7
80799 München

Room: 113
Phone: +49 (0)89 2180 73462

Website: Google Scholar profile

Research focus

I am part of the research training group Dataninja (Trustworthy AI for Seamless Problem Solving: Next Generation Intelligence Joins Robust Data Analysis, https://dataninja.nrw), funded by the German federal state of North Rhine-Westphalia. My research goal is to develop better approximation techniques for the Shapley value. A game-theoretic concept to fairly distribute collective benefits achieved by a group of agents. It is commonly used in Explainable AI to attribute feature importance but also quantify the significance of data points, base learners in ensembles, and neurons in neural networks, among many other applications.

Research areas

  • Explainable AI, Bandit Algorithms

Publications