Machine Learning for Computer Vision and Natural Language Processing

Focus of our research

Machine learning has changed major industries around the world, and its impact is felt in many areas of our day-to-day life. New machine learning methods are needed to tackle the big data world we live in, especially in challenging areas such as computer vision and natural language processing. Such new methods need to effectively train very large models, usually in the form of deep neural networks or large probabilistic models. This is a big challenge both algorithmically and in its implementation on high-performance computers.

Research on deep and other machine learning methods is done in the context of:

• real-world computer vision problems from biomedical and health applications
• smart cities and autonomous driving
• challenging natural language processing tasks.