Dr. Anna Dawid, Leiden University

Leuchs-Russell Auditorium, A.1.500, Staudtstr. 2, Erlangen
Location Details

Abstract
The importance of machine learning (ML) in quantum physics has been rising, especially in studies of quantum phases of matter or finding ground states of interacting Hamiltonians. The more widespread its use, the more urgent the critical questions of how to extract meaningful physical insights from ML. This talk will discuss the differences between explaining a trained network’s behavior and building interpretable neural networks from the ground up. Using two case studies from our research - neural networks applied to the Su-Schrieffer-Heeger (SSH) model and the TetrisCNN model tailored to detecting phase transitions and their order parameters from experimental snapshots taken in Rydberg quantum simulators - we will show the limitations of post-hoc explainability and the advantages of interpretable architectures. We argue that the most insightful interpretable models for non-tabular data are largely task-dependent, and we share our recipe for their design.