Synergizing Nanophotonics and Artificial Intelligence: From Inverse Design to Intelligent Optical Frontends Qizhou Wang, Ph.D. Student, Electrical and Computer Engineering Apr 2, 13:00 - 15:00 B3 R5220 AI artificial intelligence nanophotonics computational imaging deep learning Computer Vision hyperspectral imaging intelligent systems This dissertation investigates the transformative convergence of nanophotonics and artificial intelligence (AI).
Metasurface Based Optical Metrology Systems: Design, Fabrication, and Implementations Arturo Burguete Lopez, Ph.D. Student, Electrical and Computer Engineering Apr 27, 11:00 - 13:00 B3 L5 R5209 Metasurfaces integrated optics This dissertation introduces a framework to advance optical metasurfaces from individual components to integrated optical instruments, it presents demonstrations of metrology techniques that combine machine learning and nanophotonic technologies for remote sensing that outperform methods based on conventional optics, thus advancing the next generation of optical instrumentation.
Enhancing Solar Fuel Production Performance through Catalyst Design and Device Engineering Fei Xiang, Ph.D. Student, Electrical and Computer Engineering Apr 13, 14:00 - 16:00 B2 L5 R5209 This thesis integrates catalyst design and device engineering to enhance solar fuel production performance. Our work focuses on expanding the scope of solar fuels beyond hydrogen in PV-EC systems and improving the efficiency and long-term stability of the photoanode in PEC water splitting, thereby enhancing solar energy utilization.
Machine learning in hardware via trained metasurface encoders: theory, design and applications Maksim Makarenko, Ph.D. Student, Electrical and Computer Engineering Nov 23, 10:00 - 12:30 B2 L5 R5209 machine learning artificial intelligence photonics In this thesis, we introduce a novel concept of metasurface optical accelerators for machine learning with the corresponding end-to-end optimization framework that is robust to fabrication intolerance and can simultaneously optimize in tens of millions of degrees of freedom. The core of this technology is universal approximators, a single surface of optical nanoresonators mathematically equivalent to a single layer of an artificial neural network (ANN).
