Multi-wavelength optical information processing with deep reinforcement learning

Qiuquan Yan; Hao Ouyang; Zilong Tao; Meili Shen; Shiyin Du; Jun Zhang; Hengzhu Liu; Hao Hao; Tian Jiang

doi:10.1038/s41377-025-01846-6

Your Location：

Home >

Browse articles >

Multi-wavelength optical information processing with deep reinforcement learning

Original Articles

- Multi-wavelength optical information processing with deep reinforcement learning
- Multi-wavelength optical information processing with deep reinforcement learning
- LSA 2025年14卷第6期页码：1643-1654
- Affiliations：
  
  1.College of Computer Science and Technology, National University of Defense Technology, Changsha, China
  2.Institute for Quantum Science and Technology, College of Science, National University of Defense Technology, Changsha, China
  3.National Innovation Institute of Defense Technology, Academy of Military Science PLA, Beijing, China
  4.College of Advanced Interdisciplinary Studies, National University of Defense Technology, Changsha, China
  5.Hunan Research Center of the Basic Discipline for Physical States, National University of Defense Technology, Changsha, China
- Author bio：
  
  Jun Zhang (zhangjun12a@nudt.edu.cn)
  Hao Hao (HH65637917@163.com)
  Tian Jiang (tjiang@nudt.edu.cn)
- Funds：
- DOI：10.1038/s41377-025-01846-6
  中图分类号：
- 收稿日期：2024-09-20，
  
  修回日期：2025-03-16，
  
  录用日期：2025-03-21，
  
  网络出版日期：2025-04-15，
  
  纸质出版日期：2025-06-30
- Accepted：
Scan QR Code
Multi-wavelength optical information processing with deep reinforcement learning[J]. LSA, 2025,14(6):1643-1654.

Yan, Q. Q. et al. Multi-wavelength optical information processing with deep reinforcement learning. Light: Science & Applications, 14, 1643-1654 (2025).
Multi-wavelength optical information processing with deep reinforcement learning[J]. LSA, 2025,14(6):1643-1654. DOI： 10.1038/s41377-025-01846-6.

Yan, Q. Q. et al. Multi-wavelength optical information processing with deep reinforcement learning. Light: Science & Applications, 14, 1643-1654 (2025). DOI： 10.1038/s41377-025-01846-6.

摘要

Abstract

Multi-wavelength optical information processing systems are commonly utilized in optical neural networks and broadband signal processing. However

their effectiveness is often compromised by frequency-selective responses caused by fabrication

transmission

and environmental factors. To mitigate these issues

this study introduces a deep reinforcement learning calibration (DRC) method inspired by the deep deterministic policy gradient training strategy. This method continuously and autonomously learns from the system

effectively accumulating experiential knowledge for calibration strategies and demonstrating superior adaptability compared to traditional methods. In systems based on dispersion compensating fiber

micro-ring resonator array

and Mach-Zehnder interferometer array that use multi-wavelength optical carriers as the light source

the DRC method enables the completion of the corresponding signal processing functions within 21 iterations. This method provides efficient and accurate control

making it suitable for applications such as optical convolution computation acceleration

microwave photonic signal processing

and optical network routing.

关键词

Keywords

references

Bao, J. M. et al. Very-large-scale integrated quantum graph photonics. Nat. Photonics 17 , 573–581 (2023)..

Lin, K. Y. & Chang, K. H. Artificial intelligence and information processing: a systematic literature review. Mathematics 11 , 2420(2023)..

Sludds, A. et al. Delocalized photonic deep learning on the internet’s edge. Science 378 , 270–276 (2022)..

Chen, R. X. et al. Breaking the temporal and frequency congestion of LiDAR by parallel chaos. Nat. Photonics 17 , 306–314 (2023)..

McMahon, P. L. The physics of optical computing. Nat. Rev. Phys. 5 , 717–734 (2023)..

Feldmann, J. et al. All-optical spiking neurosynaptic networks with self-learning capabilities. Nature 569 , 208–214 (2019)..

Kitayama, K. I. et al. Novel frontier of photonics for data processing—Photonic accelerator. APL Photonics 4 , 090901 (2019)..

Shen, Y. C. et al. Deep learning with coherent nanophotonic circuits. Nat. Photonics 11 , 441–446 (2017)..

Shu, H. W. et al. Microcomb-driven silicon photonic systems. Nature 605 , 457–463 (2022)..

Zhang, J. H. et al. Compact, efficient, and scalable nanobeam core for photonic matrix-vector multiplication. Optica 11 , 190–196 (2024)..

Mehrabian, A. et al. A winograd-based integrated photonics accelerator for convolutional neural networks. IEEE J. Sel. Top. Quantum Electron. 26 , 6100312 (2020)..

Ma, P. Y. et al. Photonic independent component analysis using an on-chip microring weight bank. Opt. Express 28 , 1827–1844 (2020)..

Li, X. Y. et al. Improving broad-beam ion etching equipment through innovative ion optics design. J. Manuf. Process. 102 , 839–848 (2023)..

Xu, X. Y. et al. Photonic perceptron based on a Kerr microcomb for high-speed, scalable, optical neural networks. Laser Photonics Rev. 14 , 2000070 (2020)..

Zhang, J. et al. Coherent optical neuron control based on reinforcement learning. Opt. Lett. 48 , 1084–1087 (2023)..

Roblin, P. et al. Frequency-selective predistortion linearization of RF power amplifiers. IEEE Trans. Microw. Theory Tech. 56 , 65–76 (2008)..

Atieh, A. et al. Digital predistortion algorithm of advance coherent modulation schemes enabling radio over fiber for access networks. Proceedings of the Conference on Lasers and Electro-Optics. San Jose, CA, USA: IEEE, 2021, 1-2.

Yang, J. W. et al. High-ranging-precision FMCW LiDAR with adaptive pre-distortion of current injection to a semiconductor laser. J. Lightwave Technol. 42 , 1870–1876 (2024)..

Xiang, J. R., Tian, S. L. & Pan, H. Q. Calibration of frequency response mismatches in time‐interleaved analog‐to‐digital converter based on adaptive method. IET Commun. 17 , 807–814 (2023)..

Zhou, W. et al. PAM-4 delivery based on pre-distortion and CMMA equalization in a ROF system at 40 GHz. Opt. Commun. 416 , 61–65 (2018)..

Freire, P. et al. Artificial neural networks for photonic applications—from algorithms to implementation: tutorial. Adv. Opt. Photonics 15 , 739–834 (2023)..

Long, X. et al. In-situ wavefront correction via physics-informed neural network. Laser Photonics Rev. 18 , 2300833 (2024)..

Nguyen, H. M. et al. Artificial neural-network-based pre-distortion for high loss-budget 60-km long-reach passive optical network. IEEE Access 8 , 124824–124832 (2020)..

Lillicrap, T. P. et al. Continuous control with deep reinforcement learning. Proceedings of the 4th International Conference on Learning Representations. San Juan, Puerto Rico: ICLR, 2016.

Yan, Q. Q. et al. Low-latency deep-reinforcement learning algorithm for ultrafast fiber lasers. Photonics Res. 9 , 1493 (2021)..

Hadi, M. U. et al. Experimental assessment of digital predistortion using reinforcement learning for 5G analog radio over fiber links. Print at https://doi.org/10.36227/techrxiv.170906939.95961682/v1 https://doi.org/10.36227/techrxiv.170906939.95961682/v1 (2024).

Zhao, H. H. et al. Linearization of nonlinear frequency modulated continuous wave generation using model-based reinforcement learning. Opt. Express 30 , 20647–20658 (2022)..

Song, J. X. et al. Over-the-fiber digital predistortion using reinforcement learning. Proceedings of the 2021 European Conference on Optical Communication (ECOC). Bordeaux, France: IEEE, 2021, 1-4.

Wu, Y. B. et al. Symbol-based over-the-air digital predistortion using reinforcement learning. Proceedings of the IEEE International Conference on Communications. Seoul, Korea, Republic of: IEEE, 2022, 2615-2620.

Deng, L. The MNIST database of handwritten digit images for machine learning research [best of the web ] . IEEE Signal Process. Mag. 29 , 141–142 (2012)..

Salamon, J, Jacoby, C & Bello, J. P. A dataset and taxonomy for urban sound research. Proceedings of the 22nd ACM International Conference on Multimedia. Orlando, FL, USA: ACM, 2014, 1041–1044, https://doi.org/10.1145/2647868.2655045 https://doi.org/10.1145/2647868.2655045 .

Miao, R. L. et al. Dual-microcomb generation via a monochromatically pumped dual-mode microresonator. Photonics Res. 12 , 163–171 (2024)..

Ye, Z. C. et al. Foundry manufacturing of tight-confinement, dispersion-engineered, ultralow-loss silicon nitride photonic integrated circuits. Photonics Res. 11 , 558 (2023)..

Mahjoubfar, A. et al. Time stretch and its applications. Nat. Photonics 11 , 341–351 (2017)..

Wang, G. Q. et al. Improved resolution optical time stretch imaging based on high efficiency in-fiber diffraction. Sci. Rep. 8 , 600 (2018)..

Li, M. et al. Reconfigurable single-shot incoherent optical signal processing system for chirped microwave signal compression. Sci. Bull. 62 , 242–248 (2017)..

Chang, B. et al. Dispersive Fourier transform based dual-comb ranging. Nat. Commun. 15 , 4990 (2024)..

Jiang, Y. S., Karpf, S. & Jalali, B. Time-stretch LiDAR as a spectrally scanned time-of-flight ranging camera. Nat. Photonics 14 , 14–18 (2020)..

Xu, X. Y. et al. 11 TOPS photonic convolutional accelerator for optical neural networks. Nature 589 , 44–51 (2021)..

Meng, X. Y. et al. Compact optical convolution processing unit based on multimode interference. Nat. Commun. 14 , 3000 (2023)..

Tait, A. N. et al. Demonstration of WDM weighted addition for principal component analysis. Opt. Express 23 , 12758–12765 (2015)..

Bai, B. W. et al. Microcomb-based integrated photonic processing unit. Nat. Commun. 14 , 66 (2023)..

Meng, X. Y. et al. On-demand reconfigurable incoherent optical matrix operator for real-time video image display. J. Lightwave Technol. 41 , 1637–1648 (2023)..

Tan, M. X. et al. Photonic signal processor based on a Kerr microcomb for real-time video image processing. Commun. Eng. 2 , 94 (2023)..

Zang, Y. B. et al. Electro-optical neural networks based on time-stretch method. IEEE J. Sel. Top. Quantum Electron. 26 , 1–10 (2020)..

Lin, Z. X. et al. High-speed serial deep learning through temporal optical neurons. Opt. Express 29 , 19392–19402 (2021)..

Huang, L. & Yao, J. P. Optical processor for a binarized neural network. Opt. Lett. 47 , 3892–3895 (2022)..

Xu, S. F. et al. High-order tensor flow processing using integrated photonic circuits. Nat. Commun. 13 , 7970 (2022)..

Xu, S. F. et al. Analog spatiotemporal feature extraction for cognitive radio-frequency sensing with integrated photonics. Light Sci. Appl. 13 , 50 (2024)..

Cheng, J. W. et al. A small microring array that performs large complex-valued matrix-vector multiplication. Front. Optoelectron. 15 , 15 (2022)..

Ouyang, H. et al. Parallel edge extraction operators on chip speed up photonic convolutional neural networks. Opt. Lett. 49 , 838–841 (2024)..

Tao, Z. H. et al. Highly reconfigurable silicon integrated microwave photonic filter towards next-generation wireless communication. Photonics Res. 11 , 682–694 (2023)..

Zhang, W. P. et al. Silicon microring synapses enable photonic deep learning beyond 9-bit precision. Optica 9 , 579–584 (2022)..

Fan, L. L. et al. Experimental realization of convolution processing in photonic synthetic frequency dimensions. Sci. Adv. 9 , eadi4956 (2023)..

Tait, A. N. et al. Feedback control for microring weight banks. Opt. Express 26 , 26422–26443 (2018)..

Cheng, J. W. et al. Self-calibrating microring synapse with dual-wavelength synchronization. Photonics Res. 11 , 347–356 (2023)..

Reck, M. et al. Experimental realization of any discrete unitary operator. Phys. Rev. Lett. 73 , 58–61 (1994)..

Miller, D. A. B. Reconfigurable add-drop multiplexer for spatial modes. Opt. Express 21 , 20220–20229 (2013)..

Clements, W. R. et al. Optimal design for universal multiport interferometers. Optica 3 , 1460–1465 (2016)..

Zhang, H. et al. An optical neural chip for implementing complex-valued neural network. Nat. Commun. 12 , 457 (2021)..

Huang, Y. et al. Easily scalable photonic tensor core based on tunable units with single internal phase shifters. Laser Photonics Rev. 17 , 2300001 (2023)..

Abdul, Z. K. & Al-Talabani, A. K. Mel frequency cepstral coefficient and its applications: a review. IEEE Access 10 , 122136–122158 (2022)..

Cortes, C, Mohri, M & Rostamizadeh, A L 2 regularization for learning kernels. Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence. Montreal, Canada: ACM, 2009, 109–116..

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

暂无数据