Research Topics of Machine Learning Group

Deep Learning

We develop and evaluate novel deep architectures for a variety of complex realworld tasks such as image classification, vision-based force estimation, sentiment analysis, visual question answering, image quality assessment, time series analysis and face morphing detection.

Read more

Interpretable Machine Learning

Deep neural networks are usually applied in a black box manner, i.e., no information is provided about what exactly makes them arrive at their predictions. We develop techniques for visualizing, explaining and interpreting the reasoning of these complex systems.

Read more

Machine Learning & Communications

In our research we investigate the intersection between machine learning and communication technology. For instance, we develop compressed domain video analysis algorithms, which operate with the data encoded in compressed video bitstream.

Read more

Compression of Neural Networks

State-of-the-art neural networks have millions of parameters and require extensive computational resources. Our research focuses on the development of techniques for reducing the complexity and increasing the execution efficiency of these models.

Read more

Image Quality Assessment

We develop novel deep architectures for no-reference and full-reference image quality assessment and investigate EEG-based techniques for extracting brain correlates of perceived quality.

Read more

Analysis of Biomedical Data

We develop new learning methods for the analysis of biomedical data, including EEG and fMRI signals as well as proteomics data. Since real-world data is often nonstationary and contains outliers, our research in particular focuses on robust machine learning algorithms.

Read more