Der zentrale Ansprechpartner für KI an der TH Köln.
A collaborative research paper by scientists from THK-AI Research Cluster, Toyota Research Institute, and Toyota Gazoo Racing Europe has been accepted at the prestigious NeurIPS 2025 conference. The paper, titled „From Faults to Features: Pretraining to Learn Robust Representations against Sensor Failures,“ introduces a novel pretraining approach to enhance the reliability of AI models in safety-critical applications like autonomous driving.
From the abstract: „As AI technologies rapidly reshape societies, they pose both tremendous opportunities and serious risks—especially to fundamental rights. In … Mehr
Here is an overview: The Special Issue on Learning and Intelligent Optimization of the ACM Transactions on Evolutionary Learning and … Mehr
Two papers from THK-AI members were accepted for presentation at the 35th Workshop on Computational Intelligence in Berlin, November 2025, and will be published as open access in the KIT Verlag proceedings. The first paper, by Aleksandr Subbotin and Thomas Bartz-Beielstein, explores combining machine learning with classical filtering methods. The second paper, a collaboration with Everllence SE, introduces new measures to enhance explainability in artificial intelligence.
The ACM Transactions on Evolutionary Learning and Optimization publishes original papers in all areas of evolutionary computation and related areas such as … Mehr
Prof. Bartz-Beielstein’s talk „Surrogate Model-Based Multi-Objective Optimization Using DesirabilityFunctions“ was presented at ACM Genetic and Evolutionary Computation Conference in Malaga. … Mehr
The title of his talks is: „Surrogate Model-Based Multi-Objective Optimization UsingDesirability Functions“ Abstract: The desirability function approach is an established … Mehr
The Genetic and Evolutionary Computation Conferences present the latest high-quality results in the growing field of genetic and evolutionary computation. … Mehr
