Supercontinuum spectral evolution prediction by recurrent neural network
2020 Conference on Lasers and Electro-Optics (CLEO), 2020•ieeexplore.ieee.org
… Abstract: We use recurrent neural network to successfully predict the spectral evolution of
cohererent supercontinuum along propagation in an optical fiber. The … In this work, we
show how a LSTM recurrent neural network is able to learn and predict solely from the input
pulse parameters, the complex SC spectral evolution dynamics. A schematic of the neural
network is shown in Fig. 1. The RNN input is a matrix Sd−1 ∈ RD×N consisting of SC …
cohererent supercontinuum along propagation in an optical fiber. The … In this work, we
show how a LSTM recurrent neural network is able to learn and predict solely from the input
pulse parameters, the complex SC spectral evolution dynamics. A schematic of the neural
network is shown in Fig. 1. The RNN input is a matrix Sd−1 ∈ RD×N consisting of SC …
We use recurrent neural network to successfully predict the spectral evolution of cohererent supercontinuum along propagation in an optical fiber. The network performs particularly well for a wide range of input pulse parameters.
ieeexplore.ieee.org
以上显示的是最相近的搜索结果。 查看全部搜索结果