From Many-Body Hamiltonians to Machine Learning and Back
CECAM-DE-MM1P, Dahlem, Berlin, Germany
A crucial question is how to numerically represent a system as input for the ML algorithms. Despite recent progress, understanding of what makes a representation well suited for QM/ML models is still incomplete, in particular when comparing different systems. Various representations have been proposed, but systematic, constructive development based on theoretical understanding is still lacking.
This workshop brings together the leading experts working on representations for models combining quantum chemistry with machine learning to address the following questions:
- What are advantages and disadvantages of current representations?
- What are the underlying principles that make a representation well suited for QM/ML models?
- Which physical insights can be gained from models using particular representations?
- What are the most promising research directions for future representations?
The workshop will contribute to a better theoretical foundation for research on representations for QM/ML models and provide the ideas necessary for developing improved representations.
Matthias Rupp ( Fritz Haber Institute of the Max Planck Society ) - Organiser
Alexandre Tkachenko ( University of Luxembourg ) - Organiser