[1] K. O’shea, R. Nash. An introduction to convolutional neural networks. arXiv(2015).

[2] A. Sherstinsky. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D, 404, 132306(2020).

[3] N. Parmar, A. Vaswani, J. Uszkoreit. Image transformer. International Conference on Machine Learning(2018).

[4] X. Sui, Q. Wu, J. Liu. A review of optical neural networks. IEEE Access, 8, 70773-70783(2020).

[5] J. Liu, Q. Wu, X. Sui. Research progress in optical neural networks: theory, applications and developments. PhotoniX, 2(2021).

[6] E. Paolini, L. De Marinis, M. Cococcioni. Photonic-aware neural networks. Neural Comput. Appl., 34, 15589-15601(2022).

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

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

[9] Y. Chen, M. Nazhamaiti, H. Xu. All-analog photoelectronic chip for high-speed vision tasks. Nature, 623, 48-57(2023).

[10] O. Kulce, D. Mengu, Y. Rivenson. All-optical information-processing capacity of diffractive surfaces. Light Sci. Appl., 10, 25(2021).

[11] M. S. S. Rahman, J. Li, D. Mengu. Ensemble learning of diffractive optical networks. Light Sci. Appl., 10, 14(2021).

[12] J. Li, D. Mengu, N. T. Yardimci. Spectrally encoded single-pixel machine vision using diffractive networks. Sci. Adv., 7, eabd7690(2021).

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

[14] M. Miscuglio, Z. Hu, S. Li. Massively parallel amplitude-only Fourier neural network. Optica, 7, 1812-1819(2020).

[15] T. Yan, J. Wu, T. Zhou. Fourier-space diffractive deep neural network. Phys. Rev. Lett., 123, 023901(2019).

[16] W. Shi, Z. Huang, H. Huang. LOEN: lensless opto-electronic neural network empowered machine vision. Light Sci. Appl., 11, 121(2022).

[17] H. Zheng, Q. Liu, I. I. Kravchenko. Intelligent multi-channel meta-imagers for accelerating machine vision. arXiv(2023).

[18] T. Wang, M. M. Sohoni, L. G. Wright. Image sensing with multilayer nonlinear optical neural networks. Nat. Photonics, 17, 408-415(2023).

[19] Z. Huang, W. Shi, S. Wu. Pre-sensor computing with compact multilayer optical neural network. Sci. Adv., 10, eado8516(2024).

[20] M. H. Tahersima, K. Kojima, T. Koike-Akino. Deep neural network inverse design of integrated photonic power splitters. Sci. Rep., 9, 1368(2019).

[21] Y. Qu, H. Zhu, Y. Shen. Inverse design of an integrated-nanophotonics optical neural network. Sci. Bull., 65, 1177-1183(2020).

[22] R. Rojas, R. Rojas. The backpropagation algorithm. Neural Networks: A Systematic Introduction, 149-182(1996).

[23] J. Leonard, M. A. Kramer. Improvement of the backpropagation algorithm for training neural networks. Comput. Chem. Eng., 14, 337-341(1990).

[24] Z. Wang, C. Li, P. Lin. In situ training of feed-forward and recurrent convolutional memristor networks. Nat. Mach. Intell., 1, 434-442(2019).

[25] T. Zhou, L. Fang, T. Yan. In situ optical backpropagation training of diffractive optical neural networks. Photonics Res., 8, 940-953(2020).

[26] X. Guo, T. D. Barrett, Z. M. Wang. Backpropagation through nonlinear units for the all-optical training of neural networks. Photonics Res., 9, B71-B80(2021).

[27] L. G. Wright, T. Onodera, M. M. Stein. Deep physical neural networks trained with backpropagation. Nature, 601, 549-555(2022).

[28] Y. Huo, H. Bao, Y. Peng. Optical neural network via loose neuron array and functional learning. Nat. Commun., 14, 2535(2023).

[29] Z. Zheng, Z. Duan, H. Chen. Dual adaptive training of photonic neural networks. Nat. Mach. Intell., 5, 1119-1129(2023).

[30] I. Oguz, J. Ke, Q. Weng. Forward–forward training of an optical neural network. Opt. Lett., 48, 5249-5252(2023).

[31] X. Yuan, Y. Wang, Z. Xu. Training large-scale optoelectronic neural networks with dual-neuron optical-artificial learning. Nat. Commun., 14, 7110(2023).

[32] A. Momeni, B. Rahmani, M. Malléjac. Backpropagation-free training of deep physical neural networks. Science, 382, 1297-1303(2023).

[33] M. Nakajima, K. Inoue, K. Tanaka. Physical deep learning with biologically inspired training method: gradient-free approach for physical hardware. Nat. Commun., 13, 7847(2022).

[34] Z. Xue, T. Zhou, Z. Xu. Fully forward mode training for optical neural networks. Nature, 632, 280-286(2024).

[35] D. J. Gauthier, E. Bollt, A. Griffith. Next generation reservoir computing. Nat. Commun., 12(2021).

[36] M. Yan, C. Huang, P. Bienstman. Emerging opportunities and challenges for the future of reservoir computing. Nat. Commun., 15, 2056(2024).

[37] D. Brunner, M. C. Soriano, G. Van der Sande. Photonic reservoir computing. Gruyter, 8, 19(2019).

[38] S. Sunada, A. Uchida. Photonic reservoir computing based on nonlinear wave dynamics at microscale. Sci. Rep., 9, 19078(2019).

[39] S. Phang. Photonic reservoir computing enabled by stimulated Brillouin scattering. Opt. Express, 31, 22061-22074(2023).

[40] G. Tanaka, T. Yamane, J. B. Héroux. Recent advances in physical reservoir computing: A review. Neural Netw., 115, 100-123(2019).

[41] G. Hinton. The forward-forward algorithm: some preliminary investigations. arXiv(2022).

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

[43] M. A. Nahmias, B. J. Shastri, A. N. Tait. A leaky integrate-and-fire laser neuron for ultrafast cognitive computing. IEEE J. Sel. Top. Quantum Electron., 19(2013).

[44] C. Teng, J. Zou, X. Tang. MoS₂ as nonlinear optical material for optical neural networks. IEEE J. Sel. Top. Quantum Electron., 29(2023).

[45] G. K. Lim, Z. L. Chen, J. Clark. Giant broadband nonlinear optical absorption response in dispersed graphene single sheets. Nat. Photonics, 5, 554-560(2011).

[46] W. Shi, X. Jiang, Z. Huang. Lensless opto-electronic neural network with quantum dot nonlinear activation. Photonics Res., 12, 682-690(2024).

[47] M. Miscuglio, A. Mehrabian, Z. Hu. All-optical nonlinear activation function for photonic neural networks. Opt. Mater. Express, 8, 3851-3863(2018).

[48] Y. LeCun, B. Boser, J. S. Denker. Backpropagation applied to handwritten zip code recognition. Neural Comput., 1, 541-551(1989).

[49] https://yann.lecun.com/exdb/mnist/. https://yann.lecun.com/exdb/mnist/

[50] A. Krizhevsky, G. Hinton. Learning multiple layers of features from tiny images, 7(2009).

[51] https://www.cs.toronto.edu/~kriz/cifar.html. https://www.cs.toronto.edu/~kriz/cifar.html

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

[53] https://tensorflow.google.cn/datasets/catalog/fashion_mnist. https://tensorflow.google.cn/datasets/catalog/fashion_mnist