Researching | High-speed and versatile ONN through parametric-based nonlinear computation

Photonics Research, Volume. 13, Issue 6, 1647(2025)

High-speed and versatile ONN through parametric-based nonlinear computation

Xin Dong^1、†, Yuanjia Wang^1、†, Xiaoxiao Wen¹, Yi Zhou^1,2,3、*, and Kenneth K. Y. Wong^1,2,4、*

Author Affiliations

¹Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, China

²Advanced Biomedical Instrumentation Centre, Hong Kong, China

³e-mail: zhouyi08@hku.hk

⁴e-mail: kywong@eee.hku.hk

show less

Full Text Get PDF

Figures&Tables (6)

References (26)

Paper Information

References(26)

[1] M. Baek, F. DiMaio, I. Anishchenko. Accurate prediction of protein structures and interactions using a three-track neural network. Science, 373, 871-876(2021).

[2] J. Jumper, R. Evans, A. Pritzel. Highly accurate protein structure prediction with AlphaFold. Nature, 596, 583-589(2021).

[3] M. Partridge. Spectra evolution during coating(2019).

[4] Y. Rivenson, Z. Göröcs, H. Günaydin. Deep learning microscopy. Optica, 4, 1437-1443(2017).

[5] D. Patterson, J. Gonzalez, Q. Le. Carbon emissions and large neural network training. arXiv(2021).

[6] M. Asghari, A. V. Krishnamoorthy. Energy-efficient communication. Nat. Photonics, 5, 268-270(2011).

[7] A. Momeni, R. Fleury. Electromagnetic wave-based extreme deep learning with nonlinear time-Floquet entanglement. Nat. Commun., 13, 2651(2022).

[8] S. Bavikadi, A. Dhavlle, A. Ganguly. A survey on machine learning accelerators and evolutionary hardware platforms. IEEE Des. Test, 39, 91-116(2022).

[9] G. Wetzstein, A. Ozcan, S. Gigan. Inference in artificial intelligence with deep optics and photonics. Nature, 588, 39-47(2020).

[10] J. Spall, X. Guo, A. I. Lvovsky. Hybrid training of optical neural networks. Optica, 9, 803-811(2022).

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

[12] D. Huang, Y. Shi, F. Li. Fourier domain mode locked laser and its applications. Sensors, 22, 3145(2022).

[13] J. Kang, P. Feng, X. Wei. 102-nm, 44.5-MHz inertial-free swept source by mode-locked fiber laser and time stretch technique for optical coherence tomography. Opt. Express, 26, 4370-4381(2018).

[14] A. Mahjoubfar, D. V. Churkin, S. Barland. Time stretch and its applications. Nat. Photonics, 11, 341-351(2017).

[15] S. R. Dubey, S. K. Singh, B. B. Chaudhuri. Activation functions in deep learning: a comprehensive survey and benchmark. Neurocomputing, 503, 92-108(2022).

[16] U. Teğin, M. Yıldırım, İ. Oğuz. Scalable optical learning operator. Nat. Comput. Sci., 1, 542-549(2021).

[17] J. Shi, L. Zhou, T. Liu. Multiple-view D²NNs array: realizing robust 3D object recognition. Opt. Lett., 46, 3388-3391(2021).

[18] H. Dou, Y. Deng, T. Yan. Residual D²NN: training diffractive deep neural networks via learnable light shortcuts. Opt. Lett., 45, 2688-2691(2020).

[19] P. L. McMahon, A. Marandi, Y. Haribara. A fully programmable 100-spin coherent Ising machine with all-to-all connections. Science, 354, 614-617(2016).

[20] T. Zhou, F. Scalzo, B. Jalali. Nonlinear Schrödinger kernel for hardware acceleration of machine learning. J. Lightwave Technol., 40, 1308-1319(2022).

[21] X. Jiang, D. Wang, X. Chen. “Physics-informed neural network for optical fiber parameter estimation from the nonlinear Schrödinger equation. J. Lightwave Technol., 40, 7095-7105(2022).

[22] M. Nakajima, K. Tanaka, T. Hashimoto. Neural Schrödinger equation: physical law as deep neural network. IEEE Trans. Neural Netw. Learn. Syst., 33, 2686-2700(2021).

[23] C. S. Brès, A. Della Torre, D. Grassani. Supercontinuum in integrated photonics: generation, applications, challenges, and perspectives. Nanophotonics, 12, 1199-1244(2023).

[24] G. Herink, B. Jalali, C. Ropers. Resolving the build-up of femtosecond mode-locking with single-shot spectroscopy at 90 MHz frame rate. Nat. Photonics, 10, 321-326(2016).

[25] K. Goda, K. K. Tsia, B. Jalali. Serial time-encoded amplified imaging for real-time observation of fast dynamic phenomena. Nature, 458, 1145-1149(2009).

[26] A. Alwosheel, S. van Cranenburgh, C. G. Chorus. Is your dataset big enough? Sample size requirements when using artificial neural networks for discrete choice analysis. J. Choice Modelling, 28, 167-182(2018).

Tools

Get Citation

Copy Citation Text

Xin Dong, Yuanjia Wang, Xiaoxiao Wen, Yi Zhou, Kenneth K. Y. Wong, "High-speed and versatile ONN through parametric-based nonlinear computation," Photonics Res. 13, 1647 (2025)

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Fiber Optics and Optical Communications

Received: Dec. 18, 2024

Accepted: Mar. 24, 2025

Published Online: May. 30, 2025

The Author Email: Yi Zhou (zhouyi08@hku.hk), Kenneth K. Y. Wong (kywong@eee.hku.hk)

DOI:10.1364/PRJ.553388

CSTR:32188.14.PRJ.553388

Topics

laser devices and laser physics

Lasers and Laser Optics

laser manufacturing

Instrumentation, Measurement and Metrology