[1] [1] Capmany J, Novak D. Microwave photonics combines two worlds［J］. Nature Photonics, 2007, 1(6): 319-330.

[2] [2] Yao J P. Microwave photonics［J］. J. of Lightwave Technol., 2009, 27(3): 314-335.

[3] [3] LeCun Y, Bengio Y, Hinton G. Deep learning［J］. Nature, 2015, 521(7553): 436-444.

[4] [4] Smith L S. Neuromorphic Systems: Past, Present and Future［M］. New York: Springer, 2010.

[5] [5] Zou W, Ma B, Xu S, et al. Towards an intelligent photonic system［J］. Science China: Information Sciences, 2020, 63(6): 1-17.

[6] [6] Ismailov V E. Approximation by neural networks with weights varying on a finite set of directions［J］. J. of Mathematical Analysis and Appl., 2012, 389(1): 72-83.

[7] [7] Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators［J］. Neural Networks, 1989, 2(5): 359-366.

[8] [8] Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks［J］. Advances in Neural Information Processing Systems, 2012, 25: 1097-1105.

[9] [9] Ephrat A, Mosseri I, Lang O, et al. Looking to listen at the cocktail party: A speaker-independent audio-visual model for speech separation［J］. ACM Trans. on Graphics, 2018, 37(4): 03619.

[10] [10] Silver D, Schrittwieser J, Simonyan K, et al. Mastering the game of go without human knowledge［J］. Nature, 2017, 550(7676): 354-359.

[11] [11] Jumper J, Evans R, Pritzel A, et al. Highly accurate protein structure prediction with AlphaFold［J］. Nature, 2021, 596(7873): 583-589.

[12] [12] Anthimopoulos M, Christodoulidis S, Ebner L, et al. Lung pattern classification for interstitial lung diseases using a deep convolutional neural network［J］. IEEE Trans. on Medical Imaging, 2016, 35(5): 1207-1216.

[13] [13] Rivenson Y, Grcs Z, Günaydin H, et al. Deep learning microscopy［J］. Optica, 2017, 4(11): 1437-1443.

[14] [14] Khan F N, Fan Q, Lu C, et al. An optical communications perspective on machine learning and its applications［J］. J. of Lightwave Technol., 2019, 37(2): 493-516.

[15] [15] Qian C, Zheng B, Shen Y, et al. Deep-learning-enabled self-adaptive microwave cloak without human intervention［J］. Nature Photonics, 2020, 14(6): 383-390.

[16] [16] Peurifoy J, Shen Y, Jing L, et al. Nanophotonic particle simulation and inverse design using artificial neural networks［J］. Science Advances, 2018, 4(6): eaar4206.

[17] [17] Azad A K, Wang L, Guo N, et al. Signal processing using artificial neural network for BOTDA sensor system［J］. Opt. Express, 2016, 24(6): 6769-6782.

[18] [18] Wang B, Wang L, Guo N, et al. Deep neural networks assisted BOTDA for simultaneous temperature and strain measurement with enhanced accuracy［J］. Opt. Express, 2019, 27(3): 2530-2543.

[19] [19] Xu S F, Zou X T, Ma B, et al. Deep-learning-powered photonic analog-to-digital conversion［J］. Light: Science & Applications, 2019, 8(1): 1-11.

[20] [20] Zou X, Xu S, Deng A, et al. Photonic analog-to-digital converter powered by a generalized and robust convolutional recurrent autoencoder［J］. Opt. Express, 2020, 28(26): 39618-39628.

[21] [21] Zou X, Xu S, Zou W. Visualizing and simplifying convolutional recurrent autoencoder for mismatch compensation of channel-interleaved photonic analog-to-digital converter［J］. Opt. Lett., 2021, 46(13): 3167-3170.

[22] [22] Zou X, Xu S, Li S, et al. Optimization of the Brillouin instantaneous frequency measurement using convolutional neural networks［J］. Opt. Lett., 2019, 44(23): 5723-5726.

[23] [23] Zhou Y, Zhang F, Shi J, et al. Deep neural network-assisted high-accuracy microwave instantaneous frequency measurement with a photonic scanning receiver［J］. Opt. Lett., 2020, 45(11): 3038-3041.

[24] [24] Sun G, Zhang F, Gao B, et al. Photonics-based 3D radar imaging with CNN-assisted fast and noise-resistant image construction［J］. Opt. Express, 2021, 29(13): 19352-19361.

[25] [25] Xu S, Wan J, Wang R, et al. Modified deep-learning-powered photonic analog-to-digital converter for wideband complicated signal receiving［J］. Opt. Lett., 2020, 45(19): 5303-5306.

[26] [26] Yi S, Xu S, Zou W. Multi-band low-noise microwave-signal-receiving system with a photonic frequency down-conversion and transfer-learning network［J］. Opt. Lett., 2021, 46(23): 5982-5985.

[27] [27] Zhou Y, Zhang F, Sun G, et al. Machine learning based LFM signal recovery for fiber-connected radar networks［C］// Optoelectronics and Communications Conf. Optical Society of America, 2021: M4B.2.

[28] [28] Liu E, Yu Z, Wan Z, et al. Linearized wideband and multi-carrier link based on TL-ANN［J］. Chinese Opt. Lett., 2021, 19(11): 113901.

[29] [29] Wan J, Xu S, Zou W. High-accuracy automatic target recognition scheme based on a photonic analog-to-digital converter and a convolutional neural network［J］. Opt. Lett., 2020, 45(24): 6855-6858.

[30] [30] Wan J, Xu S, Zou W. High-accuracy automatic target recognition scheme based on a photonic analog-to-digital converter and a convolutional neural network［J］. Opt. Lett., 2020, 45(24): 6855-6858.

[31] [31] Wang R, Xu S, Chen J, et al. Ultra-wideband signal acquisition by use of channel-interleaved photonic analog-to-digital converter under the assistance of dilated fully convolutional network［J］. Chinese Opt. Lett., 2020, 18(12): 123901.

[32] [32] Waldrop M M. The chips are down for Moores law［J］. Nature News, 2016, 530(7589): 144.

[33] [33] Shen Y, Harris N C, Skirlo S, et al. Deep learning with coherent nanophotonic circuits［J］. Nature Photonics, 2017, 11(7): 441-446.

[34] [34] Lin X, Rivenson Y, Yardimci N T, et al. All-optical machine learning using diffractive deep neural networks［J］. Science, 2018, 361(6406): 1004-1008.

[35] [35] Feldmann J, Youngblood N, Wright C D, et al. All-optical spiking neurosynaptic networks with self-learning capabilities［J］. Nature, 2019, 569(7755): 208-214.

[36] [36] Xu S, Wang J, Wang R, et al. High-accuracy optical convolution unit architecture for convolutional neural networks by cascaded acousto-optical modulator arrays［J］. Opt. Express, 2019, 27(14): 19778-19787.

[37] [37] Xu S, Wang J, Zou W. Optical patching scheme for optical convolutional neural networks based on wavelength-division multiplexing and optical delay lines［J］. Opt. Lett., 2020, 45(13): 3689-3692.

[38] [38] Xu S, Wang J, Zou W. Optical convolutional neural network with WDM-based optical patching and microring weighting banks［J］. IEEE Photon. Technol. Lett., 2020, 33(2): 89-92.

[39] [39] Xu S, Wang J, Shu H, et al. Optical coherent dot-product chip for sophisticated deep learning regression［J］. Light: Science & Applications, 2020, 10: 221.

[40] [40] Prucnal P R, Shastri B J, Thomas F D L, et al. Recent progress in semiconductor excitable lasers for photonic spike processing［J］. Adv. Opt. Photonics, 2016, 8(2): 228-299.

[41] [41] Goi E, Zhang Q, Chen X, et al. Perspective on photonic memristive neuromorphic computing［J］. PhotoniX, 2020, 1(1): 1-26.

[42] [42] Feldmann J, Youngblood N, Wright C D, et al. All-optical spiking neurosynaptic networks with self-learning capabilities［J］. Nature, 2019, 569(7755): 208-214.

[43] [43] Ma B, Chen J, Zou W. A DFB-LD-based photonic neuromorphic network for spatiotemporal pattern recognition［C］// Optical Fiber Communication Conf. Optical Society of America, 2020: M2K.2.

[44] [44] Juodawlkis P W, Twichell J C, Betts G E, et al. Optically sampled analog-to-digital converters［J］. IEEE Trans. on Microwave Theory and Techniques, 2001, 49(10): 1840-1853.

[45] [45] Zhang H, Zou W, Yang G, et al. Dual-output modulation in time-wavelength interleaved photonic analog-to-digital converter based on actively mode-locked laser［J］. Chinese Opt. Lett., 2016, 14(3): 030602.

[46] [46] Yang G, Zou W, Yu L, et al. Compensation of multi-channel mismatches in high-speed high-resolution photonic analog-to-digital converter［J］. Opt. Express, 2016, 24(21): 24061-24074.

[47] [47] Zou W, Long X, Li X, et al. Brillouin instantaneous frequency measurement with an arbitrary response for potential real-time implementation［J］. Opt. Lett., 2019, 44(8): 2045-2048.

[48] [48] Davies M E, James C J. Source separation using single channel ICA［J］. Signal Proc., 2007, 87(8): 1819-1832.

[49] [49] Smaragdis P. Blind separation of convolved mixtures in the frequency domain［J］. Neurocom., 1998, 22(1/3): 21-34.

[50] [50] Ghelfi P, Laghezza F, Scotti F, et al. A fully photonics-based coherent radar system［J］. Nature, 2014, 507(7492): 341-345.

[51] [51] Castelvecchi D. Can we open the black box of AI?［J］. Nature News, 2016, 538(7623): 20.

[52] [52] Goodman B, Flaxman S. European union regulations on algorithmic decision-making and a “right to explanation”［J］. AI Magazine, 2017, 38(3): 50-57.

[53] [53] Geirhos R, Jacobsen J H, Michaelis C, et al. Shortcut learning in deep neural networks［J］. Nature Machine Intelligence, 2020, 2(11): 665-673.

[54] [54] Zhang Q, Wu Y N, Zhu S C. Interpretable convolutional neural networks［C］// Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, 2018: 8827-8836.

[55] [55] Karpatne A, Watkins W, Read J, et al. Physics-guided neural networks (PGNN): An application in lake temperature modeling［J］. arXiv preprint, 2017, 1710.11431.

[56] [56] Borzyszkowski B, Damaszke K, Romankiewicz J, et al. Physics-guided neural networks (PGNNs) to solve differential equations for spatial analysis［J］. Bulletin of the Polish Academy of Sciences: Technical Sciences, 2021: e139391-e139391.

[57] [57] Zeiler M D, Fergus R. Visualizing and understanding convolutional networks［C］// European Conf. on Computer Vision, Springer, Cham, 2014: 818-833.

[58] [58] Itti L, Koch C, Niebur E. A model of saliency-based visual attention for rapid scene analysis［J］. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259.

[59] [59] Montavon G, Lapuschkin S, Binder A, et al. Explaining nonlinear classification decisions with deep taylor decomposition［J］. Pattern Recognition, 2017, 65: 211-222.

[60] [60] Bach S, Binder A, Montavon G, et al. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation［J］. PloS one, 2015, 10(7): e0130140.

[61] [61] Xu Z Q J, Zhang Y, Luo T, et al. Frequency principle: Fourier analysis sheds light on deep neural networks［J］. arXiv preprint, 2019, 1901.06523.

[62] [62] Zhang Y, Zhang Z, Luo T, et al. Embedding principle of loss landscape of deep neural networks［J］. arXiv preprint, 2021, 2105.14573.

[63] [63] Xu Z Q J, Zhang Y, Xiao Y. Training behavior of deep neural network in frequency domain［C］// Inter. Conf. on Neural Information Processing. Springer, 2019: 264-274.