Integrated Neuromorphic Photonics: Synapses, Neurons, and Neural Networks

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.