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

[2] R. Szeliski. Computer Vision: Algorithms and Applications(2010).

[3] A. Krizhevsky, F. Pereira, C. Burges, I. Sutskever, L. Bottou, G. E. Hinton, K. Weinberger. ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25(2012).

[4] Y. LeCun, D. Touretzky, B. Boser, J. Denker. Handwritten digit recognition with a back-propagation network. Advances in Neural Information Processing Systems, 2(1989).

[5] R. M. Haralick, L. G. Shapiro. Image segmentation techniques. Comput. Vis. Graph. Image Process., 29, 100-132(1985).

[6] S. Minaee, Y. Y. Boykov, F. Porikli. Image segmentation using deep learning: a survey. IEEE Trans. Pattern Anal. Mach. Intell., 44, 3523-3542(2021).

[7] A. Borji, M.-M. Cheng, H. Jiang. Salient object detection: a benchmark. IEEE Trans. Image Process., 24, 5706-5722(2015).

[8] H. Fu, X. Cao, Z. Tu. Cluster-based co-saliency detection. IEEE Trans. Image Process., 22, 3766-3778(2013).

[9] W. Wang, J. Shen, L. Shao. Video salient object detection via fully convolutional networks. IEEE Trans. Image Process., 27, 38-49(2017).

[10] A. Wang, M. Wang. RGB-D salient object detection via minimum barrier distance transform and saliency fusion. IEEE Signal Process. Lett., 24, 663-667(2017).

[11] A. Chaurasia, E. Culurciello. Linknet: exploiting encoder representations for efficient semantic segmentation. IEEE Visual Communications and Image Processing (VCIP), 1-4(2017).

[12] O. Russakovsky, J. Deng, H. Su. Imagenet large scale visual recognition challenge. Int. J. Comput. Vis., 115, 211-252(2015).

[13] W. Zhang, K. Itoh, J. Tanida. Parallel distributed processing model with local space-invariant interconnections and its optical architecture. Appl. Opt., 29, 4790-4797(1990).

[14] D. Powell, M. Duffy. Neural networks and statistical models. Proceedings of the Nineteenth Annual SAS Users Group International Conference, 806-814(1994).

[15] R. Hamerly, L. Bernstein, A. Sludds. Large-scale optical neural networks based on photoelectric multiplication. Phys. Rev. X, 9, 021032(2019).

[16] J. Bueno, S. Maktoobi, L. Froehly. Reinforcement learning in a large-scale photonic recurrent neural network. Optica, 5, 756-760(2018).

[17] T. W. Hughes, M. Minkov, Y. Shi. Training of photonic neural networks through in situ backpropagation and gradient measurement. Optica, 5, 864-871(2018).

[18] P. R. Prucnal, B. J. Shastri, M. C. Teich. Neuromorphic Photonics(2017).

[19] D. Pérez, I. Gasulla, P. D. Mahapatra. Principles, fundamentals, and applications of programmable integrated photonics. Adv. Opt. Photon., 12, 709-786(2020).

[20] X. Xu, M. Tan, B. Corcoran. 11 tops photonic convolutional accelerator for optical neural networks. Nature, 589, 44-51(2021).

[21] B. J. Shastri, A. N. Tait, T. Ferreira de Lima. Photonics for artificial intelligence and neuromorphic computing. Nat. Photonics, 15, 102-114(2021).

[22] J. Feldmann, N. Youngblood, M. Karpov. Parallel convolutional processing using an integrated photonic tensor core. Nature, 589, 52-58(2021).

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

[24] Y. Shen, N. C. Harris, S. Skirlo. Deep learning with coherent nanophotonic circuits. Nat. Photonics, 11, 441-446(2017).

[25] A. N. Tait, T. F. De Lima, E. Zhou. Neuromorphic photonic networks using silicon photonic weight banks. Sci. Rep., 7, 7430(2017).

[26] M. Hermans, M. Burm, T. Van Vaerenbergh. Trainable hardware for dynamical computing using error backpropagation through physical media. Nat. Commun., 6, 6729(2015).

[27] D. Brunner, M. C. Soriano, C. R. Mirasso. Parallel photonic information processing at gigabyte per second data rates using transient states. Nat. Commun., 4, 1364(2013).

[28] M. M. P. Fard, I. A. D. Williamson, M. Edwards. Experimental realization of arbitrary activation functions for optical neural networks. Opt. Express, 28, 12138-12148(2020).

[29] S. Pai, Z. Sun, T. W. Hughes. Experimentally realized in situ backpropagation for deep learning in photonic neural networks. Science, 380, 398-404(2023).

[30] G. Wetzstein, A. Ozcan, S. Gigan. Inference in artificial intelligence with deep optics and photonics. Nature, 588, 39-47(2020).

[31] I. Chakraborty, G. Saha, A. Sengupta. Toward fast neural computing using all-photonic phase change spiking neurons. Sci. Rep., 8, 12980(2018).

[32] J. Chang, V. Sitzmann, X. Dun. Hybrid optical-electronic convolutional neural networks with optimized diffractive optics for image classification. Sci. Rep., 8, 12324(2018).

[33] L. Mennel, J. Symonowicz, S. Wachter. Ultrafast machine vision with 2D material neural network image sensors. Nature, 579, 62-66(2020).

[34] Y. Zuo, B. Li, Y. Zhao. All-optical neural network with nonlinear activation functions. Optica, 6, 1132-1137(2019).

[35] X. Luo, Y. Hu, X. Ou. Metasurface-enabled on-chip multiplexed diffractive neural networks in the visible. Light Sci. Appl., 11, 158(2022).

[36] F. Ashtiani, A. J. Geers, F. Aflatouni. An on-chip photonic deep neural network for image classification. Nature, 606, 501-506(2022).

[37] T. W. Hughes, I. A. Williamson, M. Minkov. Wave physics as an analog recurrent neural network. Sci. Adv., 5, eaay6946(2019).

[38] H. Dou, Y. Deng, T. Yan. Residual D²NN: training diffractive deep neural networks via learnable light shortcuts. Opt. Lett., 45, 2688-2691(2020).

[39] J. Li, Y.-C. Hung, O. Kulce. Polarization multiplexed diffractive computing: all-optical implementation of a group of linear transformations through a polarization-encoded diffractive network. Light Sci. Appl., 11, 153(2022).

[40] M. S. S. Rahman, X. Yang, J. Li. Universal linear intensity transformations using spatially-incoherent diffractive processors. arXiv(2023).

[41] B. Bai, Y. Li, Y. Luo. All-optical image classification through unknown random diffusers using a single-pixel diffractive network. Light Sci. Appl., 12, 69(2023).

[42] C. Qian, X. Lin, X. Lin. Performing optical logic operations by a diffractive neural network. Light Sci. Appl., 9, 59(2020).

[43] S. Jiao, J. Feng, Y. Gao. Optical machine learning with incoherent light and a single-pixel detector. Opt. Lett., 44, 5186-5189(2019).

[44] Z. Wu, M. Zhou, E. Khoram. Neuromorphic metasurface. Photon. Res., 8, 46-50(2020).

[45] Z. Wu, Z. Yu. Small object recognition with trainable lens. APL Photon., 6, 071301(2021).

[46] T. Zhou, X. Lin, J. Wu. Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit. Nat. Photonics, 15, 367-373(2021).

[47] H. Chen, J. Feng, M. Jiang. Diffractive deep neural networks at visible wavelengths. Engineering, 7, 1483-1491(2021).

[48] Y. Hu, X. Luo, Y. Chen. 3D-integrated metasurfaces for full-colour holography. Light Sci. Appl., 8, 86(2019).

[49] Y. Chen, Z. Shu, S. Zhang. Sub-10 nm fabrication: methods and applications. Int. J. Extreme Manuf., 3, 032002(2021).

[50] M. Zheng, L. Shi, J. Zi. Optimize performance of a diffractive neural network by controlling the Fresnel number. Photon. Res., 10, 2667-2676(2022).

[51] H. Xiao, K. Rasul, R. Vollgraf. Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv(2017).

[52] Y. LeCun, L. Bottou, Y. Bengio. Gradient-based learning applied to document recognition. Proc. IEEE, 86, 2278-2324(1998).

[53] J. Li, D. Mengu, Y. Luo. Class-specific differential detection in diffractive optical neural networks improves inference accuracy. Adv. Photon., 1, 046001(2019).

[54] D. Mengu, Y. Luo, Y. Rivenson. Analysis of diffractive optical neural networks and their integration with electronic neural networks. IEEE J. Sel. Top. Quantum Electron., 26, 3700114(2019).