The Home of Machine Learning at Leibniz University Hannover

Founded in 1973, the Institute of Information Processing (TNT) at Leibniz University Hannover (LUH) conducts research in the areas of artificial intelligence and machine learning, audio and video signal processing and coding, image analysis, remote sensing and biomedical engineering. The institute was actively involved in the standardization of MP3, MPEG-2, AVC (H.264) as well as HEVC (H.265) and contributes to various other standards. Techniques developed at the institute are used in numerous information processing systems, for example for implants, component testing or driver assistance, and are commercially marketed in spin-off companies. Together with our partners from industry and research, we develop solutions for the effective and automated use of information.

Do you want to join us? We have open positions.

Current Spotlight
Automatic detection and assessment of damages in pipeline systems using machine learning (more...)

Video streaming
Video streaming (more...)

Algorithm Configuration (AC) aims to optimize algorithm performance by automating important decisions like hyperparameter settings and algorithm choice. Both theoretical and empirical results have shown, however, that only making these decisions once at the beginning of an algorithm run is often not optimal. Instead, the best configuration often depends on the current timestep and algorithm's state. Therefore Dynamic Algorithm Configuration (DAC) learn configuration schedules that fit the current state to improve overall performance. (more...)