At the KI2025 Conference in Potsdam, Hannes Kath from the Chair of Applied Artificial Intelligence at the University of Oldenburg and the Interactive Machine Learning department presented the research paper “Intermediate-Task Transfer Learning for Bioacoustic Data”.

KI2025 is one of the premier European conferences on artificial intelligence bringing together researchers, developers, and decision-makers from science, industry, and public administration. This year’s conference took place from 16 to 19 September in conjunction with INFORMATIK 2025.

The research demonstrates that fine-tuning transfer learning models significantly improves the analysis of large bioacoustic datasets. These findings contribute to the development of efficient tools for biodiversity monitoring  and thus provide an important step toward practical applications in ecosystem assessment.

KI2025 conference in Potsdam: Hannes Kath presented a paper