Machine Learning
The theme program provides an interdisciplinary platform to learn about and discuss a wide range of optics and photonics topics that machine learning impacts. The theme invited speakers spanning academia, industry and government institutions.
This year’s theme focuses on two subtopics. One, how is machine learning being used to improve fabrication and manufacturing of optics or by optics, such as in laser manufacturing? The other subtopic examines solvers based on machine learning approaches. Through these talks, attendees will learn about the newest machine learning technologies applied to optics and photonics and compare them with conventional approaches.
Theme Coordinators
- Groot Gregory, Synopsys Inc., USA
- Chenkai Mao, Stanford University, USA
- Ben Mills, University of Southampton, UK
Visionary Speaker
Tyler Hughes, Flexcompute, USA
Talk Title: Building the Future of Photonic Design and Simulation with Machine Learning
Invited Speakers
David Brady, Univ. of Arizona, USA
Inteferometric Focal Planes: A Case Study in LLM Research
Jonathan Fan, Stanford Univ., USA
Automated Design for Large and Manufacturable Metalenses
Priyanka Ghosh, MTC, UK
AIgorithm Driven Approaches to Nanophotonic Systems Design
Ighodalo Idehenre, Core4ce, USA
MAISY: an AI Guided Deep Learning Software Package for the Design and Fabrication of Next-Generation Optics
Yannik Mahlau, Leibniz University Hannover, Germany
Automatic Differentiation and Reinforcement Learning for Inverse Design in Nanophotonics
Dylan McGuire, Ansys, Inc., Canada
Multi-Scale Photonic Inverse Design, Optimization and Sensitivity Analysis for Advanced Optical IO
Raphael Pestourie, Georgia Institute of Technology, USA
Machine Learning-Enhanced Optimization for Metamaterial Design
Jiahui Wang, Google X, USA
End-to-End Inverse Design for Repeatable, High-Performance Silicon Photonics