EECS Seminar: Deep Learning the Properties of Electromagnetic Metamaterials

McDonnell Douglas Engineering Auditorium (MDEA)
Willie Padilla, Ph.D.

Department of Electrical and Computer Engineering
Duke University

Seminar is also available via Zoom. For Zoom link, please contact host Maxim Shcherbakov ( or Filippo Capolino (

Abstract: Electromagnetic metamaterials have realized exotic effects including negative refractive index and invisibility cloaking. Although novel electromagnetic responses and great progress toward realistic applications have been made over the last two decades, the conventional forward design process is fundamentally limited, and therefore designs explored to date are limited. I will discuss how deep learning-based inverse methods can overcome constraints of the current design approach, and I will highlight their prospects for future novel photonic applications. 

Bio: Willie Padilla is a professor at Duke University with a master's degree and doctorate in physics. He received a Young Investigator Award from the Office of Naval Research and a Presidential Early Career Award for Scientists and Engineers. Padilla is a fellow of the American Physical Society, Optical Society of America and Kavli Frontiers of Science. He is also a Web of Science Highly Cited Researcher in physics for 2018 and 2019. He heads a group working in the area of metamaterials with a focus on machine learning, computational imaging, spectroscopy and energy, and has published more than 200 peer-reviewed journal articles.