Optical Computing
MICRO-608
The course will explore the use of optics in computation. The inherent advantage of light over electronic for communicating information has been realised in fibre optics networks for telecommunications. Optical interconnections are also used in some computing systems replacing wires. A complete optical computer requires also the equivalent of transistors to carry out the nonlinearity essential for logic or decision making and therefore an optical computer needs to include nonlinear devices, either of optical or electronic origin. Optical computing has received a lot of attention recently because of the explosion of machine learning and neural networks which require dense connectivity, making these systems well matched to optics. In this course we will start with a brief history of optical computing, describe methods for implementing optical interconnection and logic and then spend most of our time on learning about the recent efforts in optical computing machines for machine learning.
List of recent papers in optical computing
- Inference in artificial intelligence with deep optics and photonics (File)
- Chen et al. - 2023 - All-analog photoelectronic chip for high-speed vis (File)
- Wu et al. - 2023 - Lithography-free reconfigurable integrated photoni (File)
- Ashtiani et al. - 2022 - An on-chip photonic deep neural network for image (File)
- Zhou et al. - 2022 - Photonic matrix multiplication lights up photonic (File)
- Wang et al. - 2022 - An optical neural network using less than 1 photon (File)
- Ising machines as hardware solvers of combinatorial optimization problems (File)
- Deep Physical Neural Networks Trained with Backpropagation (File)
- Parallel photonic information processing at gigabyte per second data rates using transient states (File)
- Computational metrics and parameters of an injection-locked large area semiconductor laser for neural network computing (File)
- Lightmatter (Company) (Folder)
- LightIntelligence (Company) (Folder)
Week 3 (March 4-8) : Introduction lecture - Professor D. Psaltis
week 4 (March 11-15): Lecture on Extreme Learning Machines by Ilker
week 5 (March 18-22): no presentation
week 6 (March 25-29): presentation by Felix Richter
week 7 (April 1-5): Easter Break
week 8 (April 8-12) : no presentations
week 9 (April 15-19) : presentation topic by Pengbo Yu
week 10 (April 22-26) : presentation by students
week 11 (April 29- May 3rd): presentation by Yazan Lampert
Large Scale photonics chiplet 160 - TOPS/Wattt