KI2025: IML presents Research on Efficient Bioacoustic Analysis

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, Read more…

Two recent interviews about generative and human-centred AI 

The Lower Saxony press (Nordwest Zeitung/NWZ) and Oldenburg’s local Mox Journal published two interviews with Prof. Sonntag discussing generative and human-centered AI. As artificial intelligence becomes a widely discussed topic, the University of Oldenburg actively conducts research in this area. In these interviews, Prof. Sonntag elaborates on his research group’s Read more…

Comprehensive Evaluation of
Feature Attribution Methods in Explainable AI via Input Perturbation

Explainable AI (XAI) has demonstrated its potential in deciphering discriminatory features in machine learning (ML) decision-making processes. Specifically, XAI’s feature attribution methods shed light on individual decisions made by ML models. However, despite their visual appeal, these attributions can be unfaithful. To ensure the faithfulness of feature attributions, it is Read more…