Yiwen Hu, Xin Liu, Cuifang Kuang, Xu Liu, Xiang Hao. Research Progress and Prospect of Adaptive Optics Based on Deep Learning[J]. Chinese Journal of Lasers, 2023, 50(11): 1101009
- Chinese Journal of Lasers
- Vol. 50, Issue 11, 1101009 (2023)
Fig. 1. Commonly used artificial neural network models. (a) Fully connected neural network; (b) convolutional neural network; (c) residual network; (d) U-Net architecture; (e) Inception architecture; (f) long short-term memory network
Fig. 2. Commonly used activation function. (a) ReLU function; (b) sigmoid function; (c) tanh function
![Structure of CNN7 model[34]](/Images/icon/loading.gif){kind=icon}
Fig. 3. Structure of CNN7 model[34]
Fig. 4. Training architecture of weights-sharing two-stream CNN framework[42]
Fig. 5. Sketch map of feature-based wavefront retrieval approach[47]
Fig. 6. Simulation results of reconstruction images [49]
Fig. 7. False rates of different methods under low signal-to-noise ratio [52]
Fig. 8. ISNet architecture[57]
Fig. 9. Architecture of SH-Net[59]. (a) Process of phase retrieval; (b) residual block architecture
Fig. 10. Diffractive neural network
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20