Photonic Integrated Neuro-synaptic Core For Convolutional Spiking Neural Network

This article discusses the development of a photonic integrated neuro-synaptic core for convolutional spiking neural networks. It highlights the advantages of photonic brain-like computing, such as high-speed, broadband, and multi-dimensional computing, and its potential applications in photonic neural network accelerators, photonic smart chips, autonomous driving, and edge computing. To solve the nonlinear computing problem of photonic neural networks, a photonic integrated synaptic chip based on DFB-SA laser was developed, which successfully simulated the intrinsic plasticity of biological neurons.