[1] Study on artificial intelligence: the state of the art and future prospects. J. Ind. Inf. Integr., 23, 100224(2021). https://doi.org/10.1016/j.jii.2021.100224

[2] . Neuromorphic photonics(2017).

[3] et alInference in artificial intelligence with deep optics and photonics. Nature, 588, 39-47(2020). https://doi.org/10.1038/s41586-020-2973-6

[4] et alAll-optical machine learning using diffractive deep neural networks. Science, 361, 1004-1008(2018). https://doi.org/10.1126/science.aat8084

[5] et alFourier-space diffractive deep neural network. Phys. Rev. Lett., 123, 023901(2019). https://doi.org/10.1103/PhysRevLett.123.023901

[6] et alA programmable diffractive deep neural network based on a digital-coding metasurface array. Nat. Electron., 5, 113-122(2022). https://doi.org/10.1038/s41928-022-00719-9

[7] et alMassively parallel universal linear transformations using a wavelength-multiplexed diffractive optical network. Adv. Photonics, 5, 016003(2023). https://doi.org/10.1117/1.AP.5.1.016003

[8] et alOptical information transfer through random unknown diffusers using electronic encoding and diffractive decoding. Adv. Photonics, 5, 046009(2023). https://doi.org/10.1117/1.AP.5.4.046009

[9] et alHybrid optical-electronic convolutional neural networks with optimized diffractive optics for image classification. Sci. Rep., 8, 12324(2018). https://doi.org/10.1038/s41598-018-30619-y

[10] et alDeep learning with coherent nanophotonic circuits. Nat. Photonics, 11, 441-446(2017). https://doi.org/10.1038/nphoton.2017.93

[11] et alAn optical neural chip for implementing complex-valued neural network. Nat. Commun., 12, 457(2021). https://doi.org/10.1038/s41467-020-20719-7

[12] et alNonlinear germanium-silicon photodiode for activation and monitoring in photonic neuromorphic networks. Nat. Commun., 13, 6048(2022). https://doi.org/10.1038/s41467-022-33877-7

[13] et alNeuromorphic photonic networks using silicon photonic weight banks. Sci. Rep., 7, 7430(2017). https://doi.org/10.1038/s41598-017-07754-z

[14] et alAll-optical spiking neurosynaptic networks with self-learning capabilities. Nature, 569, 208-214(2019). https://doi.org/10.1038/s41586-019-1157-8

[15] et alParallel convolutional processing using an integrated photonic tensor core. Nature, 589, 52-58(2021). https://doi.org/10.1038/s41586-020-03070-1

[16] In-situ nonvolatile and volatile modulation for optical neural networks. Adv. Photonics, 5, 050501(2023). https://doi.org/10.1117/1.AP.5.5.050501

[17] et alElectrically programmable phase-change photonic memory for optical neural networks with nanoseconds in situ training capability. Adv. Photonics, 5, 046004(2023). https://doi.org/10.1117/1.AP.5.4.046004

[18] et alDiffractive deep neural networks at visible wavelengths. Engineering, 7, 1483-1491(2021). https://doi.org/10.1016/j.eng.2020.07.032

[19] et alPartitionable high-efficiency multilayer diffractive optical neural network. Sensors, 22, 7110(2022). https://doi.org/10.3390/s22197110

[20] et alAll-analog photoelectronic chip for high-speed vision tasks. Nature, 623, 48-57(2023). https://doi.org/10.1038/s41586-023-06558-8

[21] et alToward software-equivalent accuracy on transformer-based deep neural networks with analog memory devices. Front. Comput. Neurosci., 15, 675741(2021). https://doi.org/10.3389/fncom.2021.675741

[22] et alDeep physical neural networks trained with backpropagation. Nature, 601, 549-555(2022). https://doi.org/10.1038/s41586-021-04223-6

[23] Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans. Neural Netw., 17, 879-892(2006). https://doi.org/10.1109/TNN.2006.875977

[24] Extreme learning machine: theory and applications. Neurocomputing, 70, 489-501(2006). https://doi.org/10.1016/j.neucom.2005.12.126

[25] et alExtreme learning machine for regression and multiclass classification. IEEE Trans. Syst. Man Cybern. B, Cybern., 42, 513-529(2012). https://doi.org/10.1109/TSMCB.2011.2168604

[26] et alA unified framework for reservoir computing and extreme learning machines based on a single time-delayed neuron. Sci. Rep., 5, 14945(2015). https://doi.org/10.1038/srep14945

[27] Photonic extreme learning machine by free-space optical propagation. Photonics Res., 9, 1446(2021). https://doi.org/10.1364/PRJ.423531

[28] et alRandom projections through multiple optical scattering: approximating kernels at the speed of light, 6215-6219(2016). https://doi.org/10.1109/ICASSP.2016.7472872

[29] et alGradient-based learning applied to document recognition. Proc. IEEE, 86, 2278-2323(1998). https://doi.org/10.1109/5.726791

[30] Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms(2017). https://arxiv.org/abs/1708.07747

[31] . Learning Multiple Layers of Features from Tiny Images(2009).

[32] . Diffraction, Fourier Optics and Imaging(2007).

[33] et alAnalysis of numerical diffraction calculation methods: from the perspective of phase space optics and the sampling theorem. J. Opt. Soc. Amer. A, 37, 1748(2020). https://doi.org/10.1364/JOSAA.401908

[34] . Discrete and Continuous Fourier Transforms: Analysis, Applications and Fast Algorithms(2008).

[35] et alLarge-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit. Nat. Photonics, 15, 367-373(2021). https://doi.org/10.1038/s41566-021-00796-w

[36] DiffPrune: neural network pruning with deterministic approximate binary gates and L0 regularization(2021). https://arxiv.org/abs/2012.03653

[37] Classification of garments from Fashion MNIST dataset using CNN LeNet-5 architecture, 238-243(2020). https://doi.org/10.1109/ITCE48509.2020.9047776

[38] et alClass-specific differential detection in diffractive optical neural networks improves inference accuracy. Adv. Photonics, 1, 046001(2019). https://doi.org/10.1117/1.AP.1.4.046001

[39] ImageNet classification with deep convolutional neural networks. Commun. ACM, 60, 84-90(2017). https://doi.org/10.1145/3065386

[40] A novel deep convolutional neural network structure for off-line handwritten digit recognition, 216-220(2019). https://doi.org/10.1145/3358528.3358585

[41] et alAn analysis of convolutional neural network for fashion images classification (Fashion-MNIST), 85-95(2020). https://doi.org/10.1007/978-3-030-50097-9_10

[42] et alRepresentational learning with ELMs for big data. IEEE Intell. Syst., 28, 31-34(2013).

[43] Clothing image classification with a dragonfly algorithm optimised online sequential extreme learning machine. Fibres Text. East. Eur., 29, 91-96(2021). https://doi.org/10.5604/01.3001.0014.7793

[44] et alTwo novel ELM-based stacking deep models focused on image recognition. Appl. Int0ell., 50, 1345-1366(2020). https://doi.org/10.1007/s10489-019-01584-4

[45] et alMulti layer multi objective extreme learning machine, 1297-1301(2017). https://doi.org/10.1109/ICIP.2017.8296491

[46] et alSupport vector machines. IEEE Intell. Syst. Appl., 13, 18-28(1998). https://doi.org/10.1109/5254.708428

[47] Classification and analysis of the MNIST dataset using PCA and SVM algorithms. Vojnotehnički glasnik, 71, 221-238(2023). https://doi.org/10.5937/vojtehg71-42689

[48] et alDeep residual learning for image recognition, 770-778(2016). https://doi.org/10.1109/CVPR.2016.90

[49] et alBenchopt: reproducible, efficient and collaborative optimization benchmarks(2022). https://arxiv.org/abs/2206.13424

[50] et alAccurate deep neural network inference using computational phase-change memory. Nat. Commun., 11, 2473(2020). https://doi.org/10.1038/s41467-020-16108-9

[51] et alA compute-in-memory chip based on resistive random-access memory. Nature, 608, 504-512(2022). https://doi.org/10.1038/s41586-022-04992-8

[52] et alAn MRAM-based deep in-memory architecture for deep neural networks, 1-5(2019). https://doi.org/10.1109/ISCAS.2019.8702206

[53] Computing in-memory with cascaded spintronic devices for AI edge. Comput. Electr. Eng., 109, 108767(2023). https://doi.org/10.1016/j.compeleceng.2023.108767

[54] et alA discrete memristive neural network and its application for character recognition. Neurocomputing, 523, 1-8(2023). https://doi.org/10.1016/j.neucom.2022.12.014

[55] et alA perovskite memristor with large dynamic space for analog-encoded image recognition. ACS Nano, 16, 21324-21333(2022). https://doi.org/10.1021/acsnano.2c09569

[56] et alEdge learning using a fully integrated neuro-inspired memristor chip. Science, 381, 1205-1211(2023). https://doi.org/10.1126/science.ade3483

[57] et alOnline dynamical learning and sequence memory with neuromorphic nanowire networks. Nat. Commun., 14, 6697(2023). https://doi.org/10.1038/s41467-023-42470-5

[58] et alMassively parallel amplitude-only Fourier neural network. Optica, 7, 1812(2020). https://doi.org/10.1364/OPTICA.408659

[59] et alHybrid optical-electronic neural network with pseudoinverse learning for classification inference. Appl. Phys. Lett., 119, 114102(2021). https://doi.org/10.1063/5.0059010

[60] Only-train-electrical-to-optical-conversion (OTEOC): simple diffractive neural networks with optical readout. Opt. Express, 30, 28024(2022). https://doi.org/10.1364/OE.462370

[61] et alLOEN: lensless opto-electronic neural network empowered machine vision. Light. Sci. Appl., 11, 121(2022). https://doi.org/10.1038/s41377-022-00809-5

[62] et alUltrafast neuromorphic photonic image processing with a VCSEL neuron. Sci. Rep., 12, 4874(2022). https://doi.org/10.1038/s41598-022-08703-1

[63] et alTraining large-scale optoelectronic neural networks with dual-neuron optical-artificial learning. Nat. Commun., 14, 7110(2023). https://doi.org/10.1038/s41467-023-42984-y

[64] et alAn optical neural network using less than 1 photon per multiplication. Nat. Commun., 13, 123(2022). https://doi.org/10.1038/s41467-021-27774-8

[65] et alSpace-efficient optical computing with an integrated chip diffractive neural network. Nat. Commun., 13, 1044(2022). https://doi.org/10.1038/s41467-022-28702-0

[66] et alLarge-scale photonic chiplet Taichi empowers 160-TOPS/W artificial general intelligence. Science, 384, 202-209(2024). https://doi.org/10.1126/science.adl1203

[67] NVIDIA H100 tensor core GPU datasheet(2024). https://resources.nvidia.com/en-us-tensor-core/nvidia-tensor-core-gpu-datasheet

[68] NVIDIA H100 tensor core GPU architecture overview(2024). https://resources.nvidia.com/en-us-tensor-core/gtc22-whitepaper-hopper

[69] et alPhotonic multiply-accumulate operations for neural networks. IEEE J. Select. Top. Quantum Electron., 26, 1-18(2020). https://doi.org/10.1109/JSTQE.2019.2941485