[1] A. Krizhevsky, I. Sutskever, G. E. Hinton. Imagenet classification with deep convolutional neural networks(2012).

[2] X. Li et al. Performance analysis of GPU-based convolutional neural networks, 67-76(2016).

[3] P. L. McMahon. The physics of optical computing. Nat. Rev. Phys., 5, 717-734(2023).

[4] J. Chang et al. Hybrid optical-electronic convolutional neural networks with optimized diffractive optics for image classification. Sci. Rep., 8, 12324(2018).

[5] S. Colburn et al. Optical frontend for a convolutional neural network. Appl. Opt., 58, 3179-3186(2019).

[6] M. Yang et al. Optical convolutional neural network with atomic nonlinearity. Opt. Express, 31, 16451-16459(2023).

[7] A. M. McNeil et al. Fundamentals and recent developments of free-space optical neural networks. J. Appl. Phys., 136, 030701(2024).

[8] H. Chen et al. Diffractive deep neural networks: theories, optimization, and applications. Appl. Phys. Rev., 11, 021332(2024).

[9] L. Cutrona et al. Optical data processing and filtering systems. IRE Trans. Inf. Theory, 6, 386-400(1960).

[10] J. N. Mait, G. W. Euliss, R. A. Athale. Computational imaging. Adv. Opt. Photonics, 10, 409-483(2018).

[11] C. M. V. Burgos et al. Design framework for metasurface optics-based convolutional neural networks. Appl. Opt., 60, 4356-4365(2021).

[12] Z. Hu et al. High-throughput multichannel parallelized diffraction convolutional neural network accelerator. Laser Photonics Rev., 16, 2200213(2022).

[13] W. Lohmann, W. T. Rhodes. Two-pupil synthesis of optical transfer functions. Appl. Opt., 17, 1141-1151(1978).

[14] J. N. Mait, W. T. Rhodes. Two-pupil synthesis of optical transfer functions: 2: pupil function relationships. Appl. Opt., 25, 2003-2007(1986).

[15] J. N. Mait. Pupil-function design for complex incoherent spatial filtering. J. Opt. Soc. Am. A, 4, 1185-1193(1987).

[16] K. Wei et al. Sci. Adv., 10(2024).

[17] J. Xiang et al. Knowledge distillation circumvents nonlinearity for optical convolutional neural networks. Appl. Opt., 61, 2173-2183(2022).

[18] A. Ryou et al. Free-space optical neural network based on thermal atomic nonlinearity. Photon. Res., 9, B128-B134(2021).

[19] T. Wang et al. Image sensing with multilayer nonlinear optical neural networks. Nat. Photonics, 17, 408-415(2023).

[20] H. Zheng et al. Meta-optic accelerators for object classifiers. Sci. Adv., 8, eabo6410(2022).

[21] T. Zhou et al. Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit. Nat. Photonics, 15, 367-373(2021).

[22] L. Huang et al. Photonic advantage of optical encoders. Nanophotonics, 13, 1191-1196(2023).

[23] H. Zheng et al. Multichannel meta-imagers for accelerating machine vision. Nat. Nanotechnol., 19, 471-478(2024).

[24] X. Lin et al. All-optical machine learning using diffractive deep neural networks. Science, 361, 1004-1008(2018).

[25] D. Mengu et al. Analysis of diffractive optical neural networks and their integration with electronic neural networks. IEEE J. Sel. Top. Quantum Electron., 26, 3700114(2020).

[26] C. He et al. Pluggable multitask diffractive neural networks based on cascaded metasurfaces. Opto-Electron. Adv., 7, 230005(2024).

[27] X. Luo et al. Metasurface-enabled on-chip multiplexed diffractive neural networks in the visible. Light Sci. Appl., 11, 158(2022).

[28] S. Öztürk et al. Convolution kernel size effect on convolutional neural network in histopathological image processing applications, 1-5(2018).

[29] H. Cai et al. Network augmentation for tiny deep learning(2022).

[30] R. W. Gerchberg. A practical algorithm for the determination of phase from image and diffraction plane pictures. Optik, 35, 237-246(1972).

[31] J. W. Goodman. Introduction to Fourier Optics(2005).

[32] K. Matsushima, T. Shimobaba. Band-limited angular spectrum method for numerical simulation of free-space propagation in far and near fields. Opt. Express, 17, 19662-19673(2009).

[33] A. Jacot et al. Saddle-to-saddle dynamics in deep linear networks: small initialization training, symmetry, and sparsity(2021).

[34] J. Ma, Y. Yuan. Dimension reduction of image deep feature using PCA. J. Visual Commun. Image Represent., 63, 102578(2019).

[35] G. Ivosev, L. Burton, R. Bonner. Dimensionality reduction and visualization in principal component analysis. Anal. Chem., 80, 4933-4944(2008).

[36] S. Hochreiter. The vanishing gradient problem during learning recurrent neural nets and problem solutions. Int. J. Uncertainty Fuzziness Knowledge Based Syst., 6, 107-116(1998).

[37] G. Seo et al. KL-divergence-based region proposal network for object detection, 2001-2005(2020).

[38] J. Xiang, E. Shlizerman. TKIL: tangent kernel optimization for class balanced incremental learning, 3529-3539(2023).

[39] Y. Zheng et al. BI-MAML: balanced incremental approach for meta learning(2020).

[40] V. Liu, S. Fan. S4: a free electromagnetic solver for layered periodic structures. Comput. Phys. Commun., 183, 2233-2244(2012).

[41] J. Chang et al. Reducing MAC operation in convolutional neural network with sign prediction, 177-182(2018).

[42] S. B. Damelin, W. Miller. The Mathematics of Signal Processing(2011).

[43] B. Dube. Phase retrieval II: iterative transform algorithms(2023).

[44] B. Dube. PRAISE(2019).