[1] LeCun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 521, 436-444(2015).

[2] Lin M X, Huang X P, Lin Z W et al. Precipitation intensity recognition was based on a convolution neural network with fused encoded and decoded features[J]. Laser & Optoelectronics Progress, 60, 0211003(2023).

[3] Leydig C, Theis L, Huszár F et al. Photo-realistic single image super-resolution using a generative adversarial network[C], 105-114(2017).

[4] Kang C, Li W X, Huang S et al. Research on an active optical correction algorithms based on deep learning[J]. Acta Optica Sinica, 41, 0611004(2021).

[5] Wang T, Dong W D, Shen K et al. Sparse-view photoacoustic image quality enhancement based on a modified U-Net[J]. Laser & Optoelectronics Progress, 59, 0617022(2022).

[6] de Lima T F, Peng H T, Tait A N et al. Machine learning with neuromorphic photonics[J]. Journal of Lightwave Technology, 37, 1515-1534(2019).

[7] Zhang Q M, Yu H Y, Barbiero M et al. Artificial neural networks enabled by nanophotonics[J]. Light: Science & Applications, 8, 1-14(2019).

[8] Xu X Y, Tan M X, Corcoran B et al. 11 TOPS photonic convolutional accelerator for optical neural networks[J]. Nature, 589, 44-51(2021).

[9] Lin X, Rivenson Y, Yardimci N T et al. All-optical machine learning using diffractive deep neural networks[J]. Science, 361, 1004-1008(2018).

[10] Zhao Y H, Wang X, Gao D S et al. On-chip programmable pulse processor employing a cascaded MZI-MRR structure[J]. Frontiers of Optoelectronics, 12, 148-156(2019).

[11] Wetzstein G, Ozcan A, Gigan S et al. Inferences in artificial intelligence with deep optics and photonics[J]. Nature, 588, 39-47(2020).

[12] Shen Y C, Harris N C, Skirlo S et al. Deep learning with coherent nanophotonic circuits[J]. Nature Photonics, 11, 441-446(2017).

[13] Hughes T W, Momchil M, Yu S et al. Training of photonic neural networks through in situ backpropagation[J]. Optica, 5, 864-871(2018).

[14] Zhang T, Wang J, Dan Y H et al. Efficient training and design of a photonic neural networks through neuroevolution[J]. Optics Express, 27, 37150-37163(2019).

[15] Zang Y B, Chen M H, Yang S G et al. Electro-optical neural networks based on time-stretch method[J]. IEEE Journal of Selected Topics in Quantum Electronics, 26, 7701410(2020).

[16] Alvear-Sandoval R F, Sancho-Gómez J L, Figueiras-Vidal A R. On improving CNN performance: the case of MNIST[J]. Information Fusion, 52, 106-109(2019).

[17] Fang M Y S, Manipatruni S, Wierzynski C et al. Design of optical neural networks with component imprecisions[J]. Optics Express, 27, 14009-14029(2019).

[18] Shokraneh F, Nezami M S, Liboiron-Ladouceur O. Theoretical and experimental analysis of a 4×4 reconfigurable MZI-based linear optical processor[J]. Journal of Lightwave Technology, 38, 1258-1267(2020).

[19] Gu J Q, Zhao Z, Feng C H et al. Toward area-efficient optical neural networks: an FFT-based architecture[C], 476-481(2020).

[20] Clements W R, Humphreys P C, Metcalf B J et al. Optimal design for universal multiport interferometers[J]. Optica, 3, 1460-1465(2016).

[21] Bao Q L, Zhang H, Ni Z H et al. Monolayer graphene as a saturable absorber in a mode-locked laser[J]. Nano Research, 4, 297-307(2011).

[22] Zheng H, Yang Z L, Liu W J et al. Improving deep neural networks using softplus units[C](2015).

[23] Zhu D Y, Lu S Y, Wang M Q et al. Efficient precision-adjustable architecture for softmax function in deep learning[J]. IEEE Transactions on Circuits and Systems II: Express Briefs, 67, 3382-3386(2020).

[24] Shastri B J, Tait A N, de Lima T F et al. Photonics for artificial intelligence and neuromorphic computing[J]. Nature Photonics, 15, 102-114(2021).

[25] Okuma N, Sato M. Non-Hermitian topological phenomena: a review[J]. Annual Review of Condensed Matter Physics, 14, 83-107(2023).