[1] B. Fasel. An introduction to bio-inspired artificial neural network architectures. Acta Neurol. Belg., 103, 6-12(2003).

[2] J. Kilian, H. T. Siegelmann. The dynamic universality of sigmoidal neural networks. Inf. Comput., 128, 48-56(1996).

[3] D. E. Rumelhart, G. E. Hinton, R. J. Williams. Learning representations by back-propagating errors. Nature, 323, 533-536(1986).

[4] W. Fedus, B. Zoph, N. Shazeer. Switch transformers: scaling to trillion parameter models with simple and efficient sparsity(2022).

[5] S. Reed et al. A generalist agent(2022).

[6] L. Bernstein et al. Freely scalable and reconfigurable optical hardware for deep learning. Sci. Rep., 11, 3144(2021).

[7] L. Ulrich. GM bets big on batteries: a new $2.3 billion plant cranks out Ultium cells to power a future line of electric vehicles. IEEE Spectr., 57, 26-31(2020).

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

[9] Y. Luo et al. Design of task-specific optical systems using broadband diffractive neural networks. Light Sci. Appl., 8, 112(2019).

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

[11] O. Kulce et al. All-optical information-processing capacity of diffractive surfaces. Light Sci. Appl., 10, 25(2021).

[12] T. Wang et al. An optical neural network using less than 1 photon per multiplication. Nat. Commun., 13, 123(2022).

[13] Y. Shen et al. Deep learning with coherent nanophotonic circuits. Nat. Photonics, 11, 441-446(2017).

[14] C. Huang et al. Demonstration of scalable microring weight bank control for large-scale photonic integrated circuits. APL Photonics, 5, 040803(2020).

[15] N. U. Dinc, D. Psaltis, D. Brunner. Optical neural networks: the 3D connection. Photoniques, 104, 34-38(2020).

[16] M. A. Al-Qadasi et al. Scaling up silicon photonic-based accelerators: challenges and opportunities. APL Photonics, 7, 020902(2022).

[17] T. Zhou et al. In situ optical backpropagation training of diffractive optical neural networks. Photonics Res., 8, 940-953(2020).

[18] R. Shao et al. Generalized robust training scheme using genetic algorithm for optical neural networks with imprecise components. Photonics Res., 10, 1868-1876(2022).

[19] H. Zhang et al. Efficient on-chip training of optical neural networks using genetic algorithm. ACS Photonics, 8, 1662-1672(2021).

[20] P. Jiang, C. A. Shoemaker, X. Liu. Time-varying hyperparameter strategies for radial basis function surrogate-based global optimization algorithm, 984-988(2017).

[21] R. Turner et al. Bayesian optimization is superior to random search for machine learning hyperparameter tuning: analysis of the black-box optimization challenge 2020(2021).

[22] D. Eriksson, D. Bindel, C. A. Shoemaker. pySOT and POAP: an event-driven asynchronous framework for surrogate optimization(2019).

[23] Y. Li et al. Hyper-parameter optimization using MARS surrogate for machine-learning algorithms. IEEE Trans. Emerg. Top. Comput. Intell., 4, 287-297(2020).

[24] C. Cartis, L. Roberts, O. Sheridan-Methven. Escaping local minima with derivative-free methods: a numerical investigation(2019).

[25] G. Tanaka et al. Recent advances in physical reservoir computing: a review. Neural Netw., 115, 100-123(2019).

[26] G.-B. Huang, Q.-Y. Zhu, C.-K. Siew. Extreme learning machine: theory and applications. Neurocomputing, 70, 489-501(2006).

[27] G. C. Valley et al. Photonic reservoir computer using speckle in multimode waveguide ring resonators. Opt. Express, 29, 19262-19277(2021).

[28] G. C. Valley et al. Classification of time-domain waveforms using a speckle-based optical reservoir computer. Opt. Express, 28, 1225-1237(2020).

[29] M. Rafayelyan et al. Large-scale optical reservoir computing for spatiotemporal chaotic systems prediction. Phys. Rev. X, 10, 041037(2020).

[30] D. Brunner et al. Parallel photonic information processing at gigabyte per second data rates using transient states. Nat. Commun., 4, 1364(2013).

[31] F. Duport et al. All-optical reservoir computing. Opt. Express, 20, 22783(2012).

[32] A. Dejonckheere et al. All-optical reservoir computer based on saturation of absorption. Opt. Express, 22, 10868-10881(2014).

[33] L. G. Wright et al. Deep physical neural networks trained with backpropagation. Nature, 601, 549-555(2022).

[34] J. Pauwels et al. Distributed Kerr non-linearity in a coherent all-optical fiber-ring reservoir computer. Front. Phys., 7, 138(2019).

[35] U. Teğin et al. Scalable optical learning operator. Nat. Comput. Sci., 1, 542-549(2021).

[36] O. Tzang et al. Adaptive wavefront shaping for controlling nonlinear multimode interactions in optical fibres. Nat. Photonics, 12, 368-374(2018).

[37] E. Deliancourt et al. Wavefront shaping for optimized many-mode Kerr beam self-cleaning in graded-index multimode fiber. Opt. Express, 27, 17311-17321(2019).

[38] U. Teğin et al. Controlling spatiotemporal nonlinearities in multimode fibers with deep neural networks. APL Photonics, 5, 030804(2020).

[39] J. Cao, Z. Lin, G.-B. Huang. Self-adaptive evolutionary extreme learning machine. Neural Process. Lett., 36, 285-305(2012).

[40] Z. Liu et al. Deep learning face attributes in the wild, 3730-3738(2015).

[41] A. Mafi. Pulse propagation in a short nonlinear graded-index multimode optical fiber. J. Lightwave Technol., 30, 2803-2811(2012).

[42] U. Teğin et al. Reusability report: predicting spatiotemporal nonlinear dynamics in multimode fibre optics with a recurrent neural network. Nat. Mach. Intell., 3, 387-391(2021).

[43] A. Klein et al. Meta-surrogate benchmarking for hyperparameter optimization(2019).

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

[45] Y. LeCun et al. Backpropagation applied to handwritten zip code recognition. Neural Comput., 1, 541-551(1989).

[46] T. Rahman et al. Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images. Comput. Biol. Med., 132, 104319(2021).

[47] M. Tan, Q. E. Le. EfficientNet: rethinking model scaling for convolutional neural networks(2020).

[48] V. Rotemberg et al. A patient-centric dataset of images and metadata for identifying melanomas using clinical context. Sci. Data, 8, 34(2021).

[49]

[50] D. Psaltis et al. Accurate numerical computation by optical convolution. Proc. SPIE, 0232, 151-156(1980).

[51] P. Kora et al. Transfer learning techniques for medical image analysis: a review. Biocybern. Biomed. Eng., 42, 79-107(2022).

[52] Z. Liu et al. Kerr self-cleaning of femtosecond-pulsed beams in graded-index multimode fiber. Opt. Lett., 41, 3675-3678(2016).

[53] DLP7000 data sheet, product information and support TI.com.

[54] C. Yao et al. Evaluating and analyzing the energy efficiency of CNN inference on high-performance GPU. Concurr. Comput. Pract. Exp., 33, e6064(2021).

[55] R. G. Regis, C. A. Shoemaker. Combining radial basis function surrogates and dynamic coordinate search in high-dimensional expensive black-box optimization. Eng. Optim., 45, 529-555(2013).