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
Multi-task Photonic Reservoir Computing: Wavelength Division Multiplexing for Parallel Computing with a Silicon Microring Resonator
Bernard J. Giron Castro, Christophe Peucheret, Darko Zibar, Francesco Da Ros
Optical Computing for Deep Neural Network Acceleration: Foundations, Recent Developments, and Emerging Directions
Sudeep Pasricha