- Research Groups
- Theory of Machine Learning
Theory of Machine Learning
Creating Autonomous Agents
A long-standing goal of reinforcement learning is to create truly autonomous systems, e.g., in robotics and in virtual environments. We are working towards this vision. To this end we aim to equip deep reinforcement learning systems with additional structure, e.g., for efficient navigation and object-oriented actions.
Machine Learning Applications and Transfer
We have several ongoing projects aiming to transfer machine learning as a technology into different application areas, in academia as well as in industry. In these activities we keep an eye on problems of general interest, like transfer learning, automated machine learning, long-term maintainability and human factors.
Optimization is underlying most of machine learning. It is used for training models, but also for tuning hyper-parameters and for automated model selection. Complementing gradient-based methods, we pursue research in the area of evolutionary optimization, where we are interested in algorithm design and provable performance guarantees.
Former Student Members
Recipe for Fast Large-scale SVM Training: Polishing, Parallelism, and more RAM!