The Machine Learning and Media Informatics Research Group is a specialised research team within the Department of Computer Science. The group is interested in several aspects of machine learning on signals and symbolic (discrete) data, such as music analysis and recommendation, audio source separation, emotion recognition, health related machine learning and industrial signal and knowledge analysis.
Research Activities
- Challenges in deep neural network learning
- sequential structure recognition and generation
- abstract pattern recognition
- design of inductive biases
- Deep learning for signal analysis:
- automatic music transcription,
- source separation
- emotion recognition
- Machine learning for signal analysis and classification,
- Media generation and style emulation
- Media knowledge representation
- Scientific and industrial applications of signal processing and machine learning.