Photonic Device
Photonic devices leverage light for computation, aiming to overcome limitations of electronic systems in speed, energy efficiency, and scalability, particularly for demanding applications like artificial intelligence. Current research focuses on developing photonic implementations of neural networks, employing various architectures such as reservoir computing, transformers, and spiking neural networks, often incorporating machine learning techniques like transfer learning and reinforcement learning for design optimization and inverse modeling. This field holds significant promise for accelerating deep learning, enabling more sustainable computing, and advancing nanophotonics through faster and more efficient design processes.
Papers
All-Photonic Artificial Neural Network Processor Via Non-linear Optics
Jasvith Raj Basani, Mikkel Heuck, Dirk R. Englund, Stefan Krastanov
POViT: Vision Transformer for Multi-objective Design and Characterization of Nanophotonic Devices
Xinyu Chen, Renjie Li, Yueyao Yu, Yuanwen Shen, Wenye Li, Zhaoyu Zhang, Yin Zhang