IMX Seminar Series - Machine Learning of Quantum Emergence

Decades of efforts in improving computing power and experimental instrumentation were driven by our desire to better understand the complex problem of quantum emergence. However, the increasing volume and variety of data made available to us today present new challenges. I will discuss how these challenges can be embraced and turned into opportunities by employing machine learning. The rigorous framework for scientific understanding physicists enjoy through our celebrated tradition requires the interpretability of any machine learning essential. I will discuss our recent results using machine learning approaches designed to be interpretable from the outset. Specifically, I will present discovering order parameters and its fluctuations in voluminous X-ray diffraction data and reconstructing atomic structure from 4D scanning transmission electron microscopy data.
Bio: Eun-Ah Kim is a professor of physics at Cornell. She received her undergraduate degrees in physics at the Seoul National University and joined the University of Illinois at Urbana-Champaign to pursue her PhD. After a postdoctoral position in Stanford she started her independent research group at Cornell as an assistant professor. Since 2014, she is in her current role as tenured professor. Her numerous awards well exceed the length of a short bio, and she is well recognized in the field for her creative approach to materials hosting strong electronic correlations and her creative approach using machine learning techniques to challenge and improve materials modeling.