[1] Goi E, Zhang Q M, Chen X et al. Perspective on photonic memristive neuromorphic computing[J]. PhotoniX, 1, 3(2020).

[2] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 60, 84-90(2017).

[3] Tompson J, Jain A, LeCun Y et al. Joint training of a convolutional network and a graphical model for human pose estimation[J]. Advances in Neural Information Processing Systems, 2, 1799-1807(2014).

[4] Hinton G, Deng L, Yu D et al. Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups[J]. IEEE Signal Processing Magazine, 29, 82-97(2012).

[5] Mikolov T, Deoras A, Povey D et al. Strategies for training large scale neural network language models[C], 196-201(2011).

[6] Chowdhary K R. Natural language processing[M]. Fundamentals of artificial intelligence, 603-649(2020).

[7] Manning C, Surdeanu M, Bauer J et al. The stanford CoreNLP natural language processing toolkit[C]. Maryland, 55-60(2014).

[8] Feng S J, Zuo C, Yin W et al. Application of deep learning technology to fringe projection 3D imaging[J]. Infrared and Laser Engineering, 49, 0303018(2020).

[9] Wang D, Li Z S, Zheng Y W et al. High-quality holographic 3D display system based on virtual splicing of spatial light modulator[J]. ACS Photonics, 10, 2297-2307(2023).

[10] Zuo C, Feng S J, Zhang X Y et al. Deep learning based computational imaging: status, challenges, and future[J]. Acta Optica Sinica, 40, 0111003(2020).

[11] Zhang N, Huang Z Q, Zhang Z A et al. Advances of optical computing and optoelectronic intelligent computing[J]. Chinese Journal of Lasers, 51, 1800001(2024).

[12] Lau J H. Recent advances and trends in advanced packaging[J]. IEEE Transactions on Components, 12, 228-252(2022).

[13] Cartlidge E. Photonic computing for sale[J]. Optics and Photonics News, 34, 26-33(2023).

[14] Shen Y C, Harris N C, Skirlo S et al. Deep learning with coherent nanophotonic circuits[J]. Nature Photonics, 11, 441-446(2017).

[15] Zhou H L, Dong J J, Cheng J W et al. Photonic matrix multiplication lights up photonic accelerator and beyond[J]. Light: Science & Applications, 11, 30(2022).

[16] Goi E, Chen X, Zhang Q M et al. Nanoprinted high-neuron-density optical linear perceptrons performing near-infrared inference on a CMOS chip[J]. Light: Science & Applications, 10, 40(2021).

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

[18] Liu R, Gillies D F. Overfitting in linear feature extraction for classification of high-dimensional image data[J]. Pattern Recognition, 53, 73-86(2016).

[19] Salam M A, Taher A, Samy M et al. The effect of different dimensionality reduction techniques on machine learning overfitting problem[J]. International Journal of Advanced Computer Science and Applications, 12, 641-655(2021).

[20] Bingham E, Mannila H. Random projection in dimensionality reduction: applications to image and text data[C], 245-250(2001).

[21] Kim M, Choi W, Choi Y et al. Transmission matrix of a scattering medium and its applications in biophotonics[J]. Optics Express, 23, 12648-12668(2015).

[22] Banerjee K S. Generalized inverse of matrices and its applications[J]. Technometrics, 15, 197(1973).

[23] Fradkin D, Madigan D. Experiments with random projections for machine learning[C], 517-522(2003).

[24] Goel N, Bebis G, Nefian A. Face recognition experiments with random projection[J]. Proceedings of SPIE, 5779, 426-437(2005).

[25] Sun M L, Song Z J, Jiang X H et al. Learning pooling for convolutional neural network[J]. Neurocomputing, 224, 96-104(2017).

[26] Bailer C, Habtegebrial T, Varanasi K et al. Fast feature extraction with CNNs with pooling layers[EB/OL]. https:∥arxiv.org/abs/1805.03096v1

[27] Markovsky I, Van Huffel S. Overview of total least-squares methods[J]. Signal Processing, 87, 2283-2302(2007).

[28] Björck Å. Least squares methods[M]. Handbook of numerical analysis, 1, 465-652(1990).

[29] Saunders C, Gammerman A, Vovk V. Ridge regression learning algorithm in dual variables[EB/OL]. https:∥www.seas.upenn.edu/~cis520/papers/dual_ridge.pdf

[30] An S J, Liu W Q, Venkatesh S. Fast cross-validation algorithms for least squares support vector machine and kernel ridge regression[J]. Pattern Recognition, 40, 2154-2162(2007).

[31] Tai Y W, Chen X G, Kim S et al. Nonlinear camera response functions and image deblurring: theoretical analysis and practice[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35, 2498-2512(2013).

[32] Hanaoka Y, Suzuki I, Sakurai T. Practical method to derive nonlinear response functions of cameras for scientific imaging[J]. Applied Optics, 50, 2401-2407(2011).

[33] Dasgupta S. Experiments with random projection[EB/OL]. https:∥arxiv.org/abs/1301.3849v1

[34] Sunada S, Kanno K, Uchida A. Using multidimensional speckle dynamics for high-speed, large-scale, parallel photonic computing[J]. Optics Express, 28, 30349-30361(2020).

[35] Lupo A, Butschek L, Massar S. Photonic extreme learning machine based on frequency multiplexing[J]. Optics Express, 29, 28257-28276(2021).

[36] Gigan S. Imaging and computing with disorder[J]. Nature Physics, 18, 980-985(2022).

[37] Wang H, Hu J Q, Morandi A et al. Large-scale photonic computing with nonlinear disordered media[J]. Nature Computational Science, 4, 429-439(2024).

[38] Wanjura C C, Marquardt F. Fully nonlinear neuromorphic computing with linear wave scattering[J]. Nature Physics, 20, 1434-1440(2024).

[39] Xia F, Kim K, Eliezer Y et al. Nonlinear optical encoding enabled by recurrent linear scattering[J]. Nature Photonics, 18, 1067-1075(2024).

[40] Yildirim M, Dinc N U, Oguz I et al. Nonlinear processing with linear optics[J]. Nature Photonics, 18, 1076-1082(2024).