Title: Probing quantum materials with the lens of machine learning
Abstract: Despite the significant progress in experimental techniques, understanding the microscopic interaction mechanisms in a quantum material remains a grand challenge. With monotonically increased experimental data, machine learning (ML) brings new hope and can serve as a new probe to study the complex interplay between the charge, orbital, spin, and lattice degrees of freedom. In this colloquium, I will introduce how ML can be used to reveal the hidden information in experimental data and elucidate the quantum materials. I will provide a few examples from our research, that 1) how ML can help identify the proximity effect, an effect that can lead to dissipationless spintronics or topological quantum computing, 2)how ML can be used to analyze spectra to reach topological materials classification, and 3) how ML can result in interfacial defects identification with unprecedented knowledge, and magnetic structure identification through architecture design. We highlight the importance of the representations and envision a variety of problems that can benefit from machine learning.
[1] https://onlinelibrary.wiley.com/doi/10.1002/advs.202004214
[2] https://aip.scitation.org/doi/10.1063/5.0049111
[3] https://arxiv.org/abs/2003.00994
[4] https://arxiv.org/abs/2109.08005
VIRTUAL Seminar on Zoom
Meeting Link: https://umd.zoom.us/j/91301075848