Petr Taborsky

Petr Taborsky is a postdoctoral researcher affiliated with the Department of Applied Mathematics and Computer Science at the Technical University of Denmark (DTU). His work focuses on artificial intelligence, machine learning, and computational methods within the Cognitive Systems group.

Research interests include Bayesian inference, deep learning generalization, and graph-based learning, with applications in high-performance computing and federated learning. Key contributions involve developing the Bayesian Cut method for clustering and analyzing gradient noise in AI models.

Recent publications highlight trends in

• European HPC/AI collaboration (2025)
• Bayesian graph cut techniques (2022)
• Statistical modeling in machine learning (2021)