Presentation Information

[TuP-G-4]Prediction of Supercontinuum Generation in Lithium Niobate Waveguides Using a Fully Connected Neural Network

○Haosheng Xiao1, Feng Ye1, H.Y. Fu2, Qian Li1 (1.School of Electronic and Computer Engineering, Peking University, Shenzhen 518055, China, 2.Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China)

Keywords:

Deep learning for photonic device and applications,Photonics in neuromorphic computing and machine learning devices

A fully connected neural network (FCNN) is constructed to predict supercontinuum generation in thin-film lithium niobate waveguides. By mapping instantaneous inputs to outputs, the FCNN can efficiently and accurately predict supercontinuum generation.