Hannes Kath from the Chair of Applied Artificial Intelligence at the University of Oldenburg and the Department of Interactive Machine Learning at the German Research Center for Artificial Intelligence (DFKI) presented the research paper „Intermediate-Task Transfer Learning für bioakustische Daten” (engl. "Intermediate-Task Transfer Learning for Bioacoustic Data") at the KI2025 conference in Potsdam.
KI2025 is one of the most important European conferences on artificial intelligence, bringing together researchers, developers, and decision-makers from academia, industry, and public administration. This year's conference took place from September 16 to 19 in conjunction with INFORMATIK 2025.
The research shows 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 represent an important step towards practical applications in ecosystem monitoring.
Hannes Kath from the Chair of Applied Artificial Intelligence at the University of Oldenburg and the Department of Interactive Machine Learning at the German Research Center for Artificial Intelligence (DFKI) presented the research paper „Intermediate-Task Transfer Learning für bioakustische Daten” (engl. "Intermediate-Task Transfer Learning for Bioacoustic Data") at the KI2025 conference in Potsdam.
KI2025 is one of the most important European conferences on artificial intelligence, bringing together researchers, developers, and decision-makers from academia, industry, and public administration. This year's conference took place from September 16 to 19 in conjunction with INFORMATIK 2025.
The research shows 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 represent an important step towards practical applications in ecosystem monitoring.
