Agentic Systems and Deep Neural Networks for Photonic Metamaterials
Artificial electromagnetic materials have transformed the field of electromagnetics, enabling exotic responses. The design of these materials is often cast as a challenging inverse problem, where a desired electromagnetic response is sought. We present an agentic framework that automates the complete end-to-end workflow of metamaterial inverse design, a scope that includes the development of the forward model itself. When prompted with a desired optical spectrum, the agent autonomously plans the research process, develops a custom deep learning forward model, accesses external simulation tools, and generates a final optimized geometry using an inverse method. This autonomous agent reasons, plans, and utilizes tools to automate complex design, paving the way for the automated industries of the future.
Willie Padilla
Dr. Paul Wang Distinguished Professor of Electrical and Computer Engineering, Duke University on September 18, 2026 at 10:15 AM in EB2 1231
Join Zoom Webinar
Willie Padilla is the Dr. Paul Wang Distinguished Professor of Electrical and Computer Engineering and director of the Metamaterials Center. A highly cited Fellow of IEEE, APS and Optica, he pioneered metamaterial perfect absorbers and negative index materials. His research advances metamaterials through machine learning, computational imaging and spectroscopy.
This lecture series features exciting and dynamic visiting and virtual speakers from across the range of ECE disciplines. Take some time every Friday morning to be inspired by these great scientists and engineers before heading into the weekend!