- Mathias Niepert (Universität Stuttgart, DE)
- Heike Clemens (für administrative Fragen)
Research at the intersection of machine learning and the sciences is revolutionizing our understanding of complex systems and accelerating scientific progress. Machine learning methods such as graph neural networks (GNNs) have emerged as a powerful tool for analyzing and modeling intricate relationships in diverse domains such as biology, social networks, and materials science. Geometric deep learning extends this capability by incorporating spatial and structural information into the learning process, enabling the extraction of meaningful insights from data with inherent geometry, like 3D point clouds or molecular structures. Moreover, machine learning is proving crucial in speeding up simulations of physical and biological processes, significantly reducing computational costs and enabling researchers to explore a broader range of hypotheses and scenarios. This synergy between machine learning, GNNs, geometric deep learning, and simulation acceleration holds tremendous promise for advancing scientific understanding and addressing complex real-world challenges. The meeting will address topics at the intersection of deep learning, simulations, and applications of ML in the sciences.