Interdisciplinary Approach

For comprehensively tackling small data challenges, we integrate and fuse contributions from computer science, mathematics, statistics/systems modeling, and biomedicine. In particular, this is reflected in the individual projects in the Project Areas A (Similarity), B (Transfer) and C (Uncertainty), often with co-leads from different disciplines. Overarching topics are addressed by the Fusion Hub. Our doctoral program SMART is key for establishing a shared language.

See the research projects

A (Similarity)

B (Transfer)

C (Uncertainty)

F (Fusion Hub)

Computer Science

Advances concepts developed in the context of deep learning, such as meta-learning, few-shot learning, and attention mechanisms.

Biomedicine

Provides a range of prototypical applications, to ensure broad generalization of the methods developed in their context.

Mathematics

Provides comprehensive mathematical theory, e.g., on parameter estimates, similarity measures, and confidence intervals, for proving the validity of the proposed methodology.