Integrated Neuromorphic Photonics: Synapses, Neurons, and Neural Networks
Xuhan Guo, Jinlong Xiang, Yujia Zhang, Yikai Su
Abstract
Ever‐growing demands of bandwidth, computing speed, and power consumption are now accelerating the transformation of computing research, as work‐at‐home becomes a new normal. Brain‐inspired photonic neuromorphic computing for artificial intelligence is raising an urgent need, and it promises orders‐of‐magnitude higher computing speed and energy efficiency compared with digital electronic counterparts. Photonic neuromorphic networks combine the efficiency of neural networks based on a non‐von Neumann architecture and the benefits of photonics to constitute a new computing paradigm. Herein, some recent advances in photonic neural networks are reviewed, including the concept, principle, key photonic components, and architectures that construct the neuromorphic systems, hoping to provide a better understanding of this emerging field.