Optical next generation reservoir computing

Hao Wang; Jianqi Hu; YoonSeok Baek; Kohei Tsuchiyama; Malo Joly; Qiang Liu; Sylvain Gigan

doi:10.1038/s41377-025-01927-6

Your Location：

Home >

Browse articles >

Optical next generation reservoir computing

Original Articles

- Optical next generation reservoir computing
- Light: Science & Applications Vol. 14, Issue 9, Pages: 2605-2615(2025)
- Affiliations：
  
  1.Laboratoire Kastler Brossel, École Normale Supérieure—Paris Sciences et Lettres (PSL) Research University, Sorbonne Université, Centre National de la Recherche Scientifique (CNRS), UMR 8552, Collège de France, 24 rue Lhomond, 75005 Paris, France
  2.State Key Laboratory of Precision Space-time Information Sensing Technology, Department of Precision Instrument, Tsinghua University, Beijing 100084, China
  3.Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, China
  4.Department of Information Physics and Computing, Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan
- Author bio：
  
  Jianqi Hu (jianqi@hku.hk)
  Qiang Liu (qiangliu@tsinghua.edu.cn)
  Sylvain Gigan (sylvain.gigan@lkb.ens.fr)
- Funds：
- DOI：10.1038/s41377-025-01927-6
  CLC：
- Received：13 January 2025，
  
  Revised：2025-05-13，
  
  Accepted：19 June 2025，
  
  Published Online：21 July 2025，
  
  Published：30 September 2025
- Accepted：
Scan QR Code
Wang, H. et al. Optical next generation reservoir computing. Light: Science & Applications, 14, 2605-2615 (2025).
DOI：

Wang, H. et al. Optical next generation reservoir computing. Light: Science & Applications, 14, 2605-2615 (2025). DOI： 10.1038/s41377-025-01927-6.

摘要

Abstract

Artificial neural networks with internal dynamics exhibit remarkable capability in processing information. Reservoir computing (RC) is a canonical example that features rich computing expressivity and compatibility with physical implementations for enhanced efficiency. Recently

a new RC paradigm known as next generation reservoir computing (NGRC) further improves expressivity but compromises its physical openness

posing challenges for realizations in physical systems. Here we demonstrate optical NGRC with computations performed by light scattering through disordered media. In contrast to conventional optical RC implementations

we directly and solely drive our optical reservoir with time-delayed inputs. Much like digital NGRC that relies on polynomial features of delayed inputs

our optical reservoir also implicitly generates these polynomial features for desired functionalities. By leveraging the domain knowledge of the reservoir inputs

we show that the optical NGRC not only predicts the short-term dynamics of the low-dimensional Lorenz63 and large-scale Kuramoto-Sivashinsky chaotic time series

but also replicates their long-term ergodic properties. Optical NGRC shows superiority in shorter training length and fewer hyperparameters compared to conventional optical RC based on scattering media

while achieving better forecasting performance. Our optical NGRC framework may inspire the realization of NGRC in other physical RC systems

new applications beyond time-series processing

and the development of deep and parallel architectures broadly.

关键词

Keywords

references

Werbos, P. J. Backpropagation through time: what it does and how to do it. Proc. IEEE 78 , 1550–1560 (1990)..

Dambre, J. et al. Information processing capacity of dynamical systems. Sci. Rep. 2 , 514 (2012)..

Jaeger, H. & Haas, H. Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 304 , 78–80 (2004)..

Yan, M. et al. Emerging opportunities and challenges for the future of reservoir computing. Nat. Commun. 15 , 2056 (2024)..

Pathak, J. et al. Model-free prediction of large spatiotemporally chaotic systems from data: a reservoir computing approach. Phys. Rev. Lett. 120 , 024102 (2018)..

Pammi, V. A. et al. Extreme events prediction from nonlocal partial information in a spatiotemporally chaotic microcavity laser. Phys. Rev. Lett. 130 , 223801 (2023)..

Bianchi, F. M. et al. Reservoir computing approaches for representation and classification of multivariate time series. IEEE Trans. Neural Netw. Learn. Syst. 32 , 2169–2179 (2021)..

Lu, Z. X. et al. Reservoir observers: model-free inference of unmeasured variables in chaotic systems. Chaos 27 , 041102 (2017)..

Kim, J. Z. et al. Teaching recurrent neural networks to infer global temporal structure from local examples. Nat. Mach. Intell. 3 , 316–323 (2021)..

Antonelo, E. A., Sch rauwen, B. & Stroobandt, D. Event detection and localization for small mobile robots using reservoir computing. Neural Netw. 21 , 862–871 (2008)..

Nakajima, K. & Fischer, I. Reservoir Computing: Theory, Physical Implementations, and Applications (Springer, 2021).

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

Appeltant, L. et al. Information processing using a single dynamical node as complex system. Nat. Commun. 2 , 468 (2011)..

Torrejon, J. et al. Neuromorphic computing with nanoscale spintronic oscillators. Nature 547 , 428–431 (2017)..

Cai, H. W. et al. Brain organoid reservoir computing for artificial intelligence. Nat. Electron. 6 , 1032–1039 (2023)..

Marković, D. et al. Physics for neuromorphic computing. Nat. Rev. Phys. 2 , 499–510 (2020)..

Mehonic, A. & Kenyon, A. J. Brain-inspired computing needs a master plan. Nature 604 , 255–260 (2022)..

Wetzstein, G. et al. Inference in artificial intelligence with deep optics and photonics. Nature 588 , 39–47 (2020)..

Gigan, S. Imaging and computing with disorder. Nat. Phys. 18 , 980–985 (2022)..

Zhou, H. L. et al. Photonic matrix multiplication lights up photonic accelerator and beyond. Light Sci. Appl. 11 , 30 (2022)..

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

Vandoorne, K. et al. Toward optical signal processing using photonic reservoir computing. Opt. Express 16 , 11182–11192 (2008)..

Paquot, Y. et al. Optoelectronic reservoir computing. Sci. Rep. 2 , 287 (2012)..

Larger, L. et al. Photonic information processing beyond Turing: an optoelectronic implementation of reservoir computing. Opt. Express 20 , 3241–3249 (2012)..

Martinenghi, R. et al. Photonic nonlinear transient computing with multiple-delay wavelength dynamics. Phys. Rev. Lett. 108 , 244101 (2012)..

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

Vinckier, Q. et al. High-performance photonic reservoir computer based on a coherently driven passive cavity. Optica 2 , 438–446 (2015)..

Duport, F. et al. Fully analogue photonic reservoir computer. Sci. Rep. 6 , 22381 (2016)..

Larger, L. et al. High-speed photonic reservoir computing using a time-delay-based architecture: million words per second classification. Phys. Rev. X 7 , 011015 (2017)..

Penkovsky, B. et al. Coupled nonlinear delay systems as deep convolutional neural networks. Phys. Rev. Lett. 123 , 054101 (2019)..

Lian, M. R. et al. Towards mixed physical node reservoir computing: light-emitting synaptic reservoir system with dual photoelectric output. Light Sci. Appl. 13 , 179 (2024)..

Vandoorne, K. et al. Experimental demonstration of reservoir computing on a silicon photonics chip. Nat. Commun. 5 , 3541 (2014)..

Brunner, D. & Fischer, I. Reconfigurable semiconductor laser networks based on diffractive coupling. Opt. Lett. 40 , 3854–3857 (2015)..

Bueno, J. et al. Reinforcement learning in a large-scale photonic recurrent neural network. Optica 5 , 756–760 (2018)..

Antonik, P. et al. Human action recognition with a large-scale brain-inspired photonic computer. Nat. Mach. Intell. 1 , 530–537 (2019)..

Dong, J. et al. Optical reservoir computing using multiple light scattering for chaotic systems prediction. IEEE J. Sel. Top. Quantum Electron. 26 , 7701012 (2020)..

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

Sunada, S. & Uchida, A. Photonic neural field on a silicon chip: large-scale, high-speed neuro-inspired computing and sensing. Optica 8 , 1388–1396 (2021)..

Ortín, S. et al. A unified framework for reservoir computing and extreme learning machines based on a single time-delayed neuron. Sci. Rep. 5 , 14945 (2015)..

Gallicchio, C. & Micheli, A. Fast and deep graph neural networks. In Proc. 34th AAAI Conference on Artificial Intelligence 3898–3905 (AAAI, 2020).

Wang, S. C. et al. Echo state graph neural networks with analogue random resistive memory arrays. Nat. Mach. Intell. 5 , 104–113 (2023)..

Lupo, A. et al. Deep photonic reservoir computer based on frequency multiplexing with fully analog connection between layers. Optica 10 , 1478–1485 (2023)..

Shen, Y. W. et al. Deep photonic reservoir computing recurrent network. Optica 10 , 1745–1751 (2023)..

Gallicchio, C., Micheli, A. & Pedrelli, L. Deep reservoir computing: a critical experimental analysis. Neurocomputing 268 , 87–99 (2017)..

Gauthier, D. J. et al. Next generation reservoir computing. Nat. Commun. 12 , 5564 (2021)..

Pyle, R. et al. Domain-driven models yield better predictions at lower cost than reservoir computers in lorenz systems. Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. 379 , 20200246 (2021)..

Cox, N. et al. Photonic next-generation reservoir computer based on distributed feedback in optical fiber. Chaos 34 , 073111 (2024)..

Wang, D. L. et al. A 103-tops/mm 2 integrated photonic computing engine enabling next-generation reservoir computing. Print at https://doi.org/10.48550/arXiv.2407.05840 https://doi.org/10.48550/arXiv.2407.05840 (2024)..

Jaurigue, L. & Lüdge, K. Reducing reservoir computer hyperparameter dependence by external timescale tailoring. Neuromorphic Comput. Eng. 4 , 014001 (2024)..

Pathak, J. et al. Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data. Chaos 27 , 121102 (2017)..

Lu, Z., Hunt, B. R. & Ott, E. Attractor reconstruction by machine learning. Chaos 28 , 061104 (2018)..

Pedrelli, L. & Hinaut, X. Hierarchical-task reservoir for online semanticanalysis from continuous speech. IEEE Trans. Neural Netw. Learn. Syst. 33 , 2654–2663 (2022)..

Barbosa, W. A. S. & Gauthier, D. J. Learning spatiotemporal chaos using next-generation reservoir computing. Chaos 32 , 093137 (2022)..

Ohana, R. et al. Kernel computations from large-scale random features obtained by optical processing units. In Proc. 2020 IEEE International Conference on Acoustics, Speech and Signal Processing 9294–9298 (IEEE, 2020).

Pierangeli, D. et al. Scalable spin-glass optical simulator. Phys. Rev. Appl. 15 , 034087 (2021)..

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰