Photonic Computing
Overview
Photonic computing studies how optical components such as interferometers, diffractive layers, resonators, and lasers can perform operations used in machine learning and optimization. Approaches include photonic tensor cores for neural-network and transformer workloads, passive diffractive processors, and reservoir computers that use a device’s physical dynamics; quantum photonic methods also explore learning and optimization with photon-based states. These systems are tested on tasks ranging from image and speech recognition to forecasting, classification, and combinatorial optimization, with energy, throughput, and accuracy compared against electronic baselines. A central challenge is turning optical speed or energy advantages into reliable end-to-end gains despite noise, limited memory and readout, encoding and precision costs, and constraints in scaling and calibrating hardware.
Latest papers
47 papers4 papers in the last four weeks, up 33% on the four weeks before. 0.0% of all new papers.