Artificial Intelligence in Nanophotonics: From Design to Optical Computing

Abstract The bidirectional convergence of artificial intelligence and nanophotonics drives photonic technologies toward unprecedented levels of intelligence and efficiency, fundamentally reshaping their design paradigms and application boundaries. With its powerful data-driven and nonlinear optimization capabilities, artificial intelligence has become a powerful tool for optical design, enabling the inverse design of nanophotonics devices while accelerating the forward computation of electromagnetic responses. Conversely, nanophotonics provides a wave-based computational platform, giving rise to novel optical neural networks that achieve high-speed parallel computing and efficient information processing. This paper reviews the latest progress in the bidirectional field of artificial intelligence and nanophotonics, analyzes the basic principles of various applications from a universal perspective, comprehensively evaluates the advantages and limitations of different research methods, and makes a forward-looking outlook on the bidirectional integration of artificial intelligence and nanophotonics, focusing on analyzing future development trends, potential applications, and challenges. The deep integration of artificial intelligence and nanophotonics is ushering in a new era for photonic technologies, offering unparalleled opportunities for fundamental research and industrial applications.