- Physical Review Journals
All JournalsPhysics Magazine
Access Provided by Xinjiang University

Physical Review Applied

Export citation

Export citation

Choose format for download:

Download Citation
  • Access by Xinjiang University

Optically accelerated extreme learning machine using hot atomic vapors

Pierre Azam and Robin Kaiser*

  • *Contact author: robin.kaiser@univ-cotedazur.fr
PDF

Phys. Rev. Applied 22, 034041 – Published 17 September, 2024

DOI: https://doi.org/10.1103/PhysRevApplied.22.034041

Abstract

Machine learning is becoming a widely used technique with impressive growth due to the diversity of problems of societal interest for which it can offer practical solutions. This increase of applications and required resources start to become limited by present-day hardware technologies. Indeed, novel machine learning subjects such as large language models or high-resolution image recognition raise the question of large computing time and energy cost of the required computation. In this context, optical platforms have been designed for several years with the goal of developing more efficient hardware for machine learning. Among different explored platforms, optical free-space propagation offers various advantages: parallelism, low energy cost, and computational speed. Here, we present a new design combining the strong and tunable nonlinear properties of a light beam propagating through a hot atomic vapor with an extreme learning machine model. We numerically and experimentally demonstrate the enhancement of the training using such free-space nonlinear propagation on an MNIST image classification task. We point out different experimental hyperparameters that can be further optimized to improve the accuracy of the platform.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (53)

  1. L. Floridi and M. Chiriatti, GPT-3: Its nature, scope, limits, and consequences, Minds Mach. 30, 681 (2020).
  2. E. Strubell, A. Ganesh, and A. McCallum, Energy and policy considerations for modern deep learning research, Proc. AAAI Conf. Artif. Intell. 34, 13693 (2020).
  3. L. Hanzlik, Y. Zhang, K. Grosse, A. Salem, M. Augustin, M. Backes, and M. Fritz, in IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (Nashville, TN, USA, 2021), pp. 3295–3304.
  4. S. Islam, J. Deng, S. Zhou, C. Pan, C. Ding, and M. Xie, in IEEE/DATE Design, Automation & Test in Europe Conference & Exhibition (Antwerp, Belgium, 2022), pp. 921–926.
  5. G. Wetzstein, A. Ozcan, S. Gigan, S. Fan, D. Englund, M. Soljačić, C. Denz, D. A. Miller, and D. Psaltis, Inference in artificial intelligence with deep optics and photonics, Nature 588, 39 (2020).
  6. A. Lupo, L. Butschek, and S. Massar, Photonic extreme learning machine based on frequency multiplexing, Opt. Express 29, 28257 (2021).
  7. M. Yildirim, I. Oguz, F. Kaufmann, M. R. Escale, R. Grange, D. Psaltis, and C. Moser, Nonlinear optical data transformer for machine learning, arXiv preprint arXiv:2208.09398.
  8. B. Fischer, M. Chemnitz, Y. Zhu, N. Perron, P. Roztocki, B. MacLellan, L. Di Lauro, A. Aadhi, C. Rimoldi, T. H. Falk et al., Neuromorphic computing via fission-based broadband frequency generation, Adv. Sci. 10, 2303835 (2023).
  9. J. Bueno, S. Maktoobi, L. Froehly, I. Fischer, M. Jacquot, L. Larger, and D. Brunner, Reinforcement learning in a large-scale photonic recurrent neural network, Optica 5, 756 (2018).
  10. X. Lin, Y. Rivenson, N. T. Yardimci, M. Veli, Y. Luo, M. Jarrahi, and A. Ozcan, All-optical machine learning using diffractive deep neural networks, Science 361, 1004 (2018).
  11. Y. Zuo, B. Li, Y. Zhao, Y. Jiang, Y.-C. Chen, P. Chen, G.-B. Jo, J. Liu, and S. Du, All-optical neural network with nonlinear activation functions, Optica 6, 1132 (2019).
  12. D. Pierangeli, G. Marcucci, and C. Conti, Photonic extreme learning machine by free-space optical propagation, Photonics Res. 9, 1446 (2021).
  13. T. Bu, H. Zhang, S. Kumar, M. Jin, P. Kumar, and Y. Huang, Efficient optical reservoir computing for parallel data processing, Opt. Lett. 47, 3784 (2022).
  14. U. Kamath, K. Graham, and W. Emara, Transformers for Machine Learning: A Deep Dive (Chapman and Hall/CRC, New York, 2022).
  15. P. M. Nadkarni, L. Ohno-Machado, and W. W. Chapman, Natural language processing: An introduction, J. Am. Med. Inform. Assoc. 18, 544 (2011).
  16. B. Jähne, H. Haußecker, and P. Geissler, in Handbook of Computer Vision and Applications (Citeseer, 1999), Vol. 2.
  17. P. L. McMahon, The physics of optical computing, Nat. Rev. Phys. 5, 717 (2023).
  18. B. Schrauwen, D. Verstraeten, and J. V. Campenhout, in Proceedings of the 15th European Symposium on Artificial Neural Networks (ESANN, Bruges, Belgium, 2007), pp. 471–482.
  19. G. V. der Sande, D. Brunner, and M. C. Soriano, Advances in photonic reservoir computing, Nanophotonics 6, 561 (2017).
  20. K. Vandoorne, P. Mechet, T. Van Vaerenbergh, M. Fiers, G. Morthier, D. Verstraeten, B. Schrauwen, J. Dambre, and P. Bienstman, Experimental demonstration of reservoir computing on a silicon photonics chip, Nat. Commun. 5, 3541 (2014).
  21. S. Bandyopadhyay, A. Sludds, S. Krastanov, R. Hamerly, N. Harris, D. Bunandar, M. Streshinsky, M. Hochberg, and D. Englund, Single chip photonic deep neural network with accelerated training, arXiv preprint arXiv:2208.01623.
  22. A. Röhm, L. Jaurigue, and K. Lüdge, Reservoir computing using laser networks, IEEE J. Sel. Top. Quantum Electron. 26, 1 (2020).
  23. F. Xia, K. Kim, Y. Eliezer, L. Shaughnessy, S. Gigan, and H. Cao, Deep learning with passive optical nonlinear mapping, arXiv preprint arXiv:2307.08558.
  24. J. Pauwels, G. Verschaffelt, S. Massar, and G. Van der Sande, Distributed Kerr non-linearity in a coherent all-optical fiber-ring reservoir computer, Front. Phys. 7, 138 (2019).
  25. G. Marcucci, D. Pierangeli, and C. Conti, Theory of Neuromorphic Computing by Waves: Machine Learning by Rogue Waves, Dispersive Shocks, and Solitons, Phys. Rev. Lett. 125, 093901 (2020).
  26. X. Xu, M. Tan, B. Corcoran, J. Wu, T. G. Nguyen, A. Boes, S. T. Chu, B. E. Little, R. Morandotti, A. Mitchell et al., Photonic perceptron based on a Kerr microcomb for high-speed, scalable, optical neural networks, Laser Photonics Rev. 14, 2000070 (2020).
  27. U. Teğin, M. Yıldırım, İ. Oğuz, C. Moser, and D. Psaltis, Scalable optical learning operator, Nat. Comput. Sci. 1, 542 (2021).
  28. D. Moss, Ultra-high bandwidth optical neuromorphic processing with Kerr soliton crystal microcombs: Scaling the network to the PetaOp regime, Authorea Preprints (2023).
  29. I. Boikov, D. Brunner, and A. De Rossi, Evanescent coupling of nonlinear integrated cavities for all-optical reservoir computing, New J. Phys. 25, 093056 (2023).
  30. F. Duport, B. Schneider, A. Smerieri, M. Haelterman, and S. Massar, All-optical reservoir computing, Opt. Express 20, 22783 (2012).
  31. Y. Paquot, F. Duport, A. Smerieri, J. Dambre, B. Schrauwen, M. Haelterman, and S. Massar, Optoelectronic reservoir computing, Sci. Rep. 2, 287 (2012).
  32. Y. K. Chembo, Machine learning based on reservoir computing with time-delayed optoelectronic and photonic systems, Chaos 30, 1054 (2020).
  33. G.-B. Huang, Q.-Y. Zhu, and C.-K. Siew, Extreme learning machine: Theory and applications, Neurocomputing 70, 489 (2006). neural Networks.
  34. J. Wang, S. Lu, S.-H. Wang, and Y.-D. Zhang, A review on extreme learning machine, Multimed. Tools. Appl. 81, 41611 (2022).
  35. W. S. Noble, What is a support vector machine?, Nat. Biotechnol. 24, 1565 (2006).
  36. T. Hofmann, B. Schölkopf, and A. J. Smola, Kernel methods in machine learning, Ann. Stat. 36, 1171 (2008).
  37. K. W. Martin, G. Phelps, N. D. Lemke, M. S. Bigelow, B. Stuhl, M. Wojcik, M. Holt, I. Coddington, M. W. Bishop, and J. H. Burke, Compact optical atomic clock based on a two-photon transition in rubidium, Phys. Rev. Appl. 9, 014019 (2018).
  38. Q. Glorieux, T. Aladjidi, P. D. Lett, and R. Kaiser, Hot atomic vapors for nonlinear and quantum optics, New J. Phys. 25, 051201 (2023).
  39. A. Ryou, J. Whitehead, M. Zhelyeznyakov, P. Anderson, C. Keskin, M. Bajcsy, and A. Majumdar, Free-space optical neural network based on thermal atomic nonlinearity, Photonics Res. 9, B128 (2021).
  40. N. A. Silva, V. Rocha, and T. D. Ferreira, Optical extreme learning machines with atomic vapors, Atoms 12, 10 (2024).
  41. G.-B. Huang, H. Zhou, X. Ding, and R. Zhang, Extreme learning machine for regression and multiclass classification, IEEE Trans. Syst., Man, Cybern., B (Cybernetics) 42, 513 (2012).
  42. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg et al., Scikit-learn: Machine learning in Python, J. Mach. Learn. Res. 12, 2825 (2011).
  43. K. Krupa, A. Tonello, B. M. Shalaby, M. Fabert, A. Barthélémy, G. Millot, S. Wabnitz, and V. Couderc, Spatial beam self-cleaning in multimode fibres, Nat. Photonics 11, 237 (2017).
  44. N. Šantić, A. Fusaro, S. Salem, J. Garnier, A. Picozzi, and R. Kaiser, Nonequilibrium Precondensation of Classical Waves in Two Dimensions Propagating through Atomic Vapors, Phys. Rev. Lett. 120, 055301 (2018).
  45. P. Azam, A. Fusaro, Q. Fontaine, J. Garnier, A. Bramati, A. Picozzi, R. Kaiser, Q. Glorieux, and T. Bienaimé, Dissipation-enhanced collapse singularity of a nonlocal fluid of light in a hot atomic vapor, Phys. Rev. A 104, 013515 (2021).
  46. Y. LeCun et al., Lenet-5, convolutional neural networks, URL: http://yann.lecun.com/exdb/lenet 20, 14 (2015).
  47. D. Schneider, The exascale era is upon us: The Frontier supercomputer may be the first to reach 1,000,000,000,000,000,000 operations per second, IEEE Spectr. 59, 34 (2022).
  48. I. Oguz, J.-L. Hsieh, N. U. Dinc, U. Teğin, M. Yildirim, C. Gigli, C. Moser, and D. Psaltis, Programming nonlinear propagation for efficient optical learning machines, Adv. Photonics 6, 016002 (2024).
  49. L. Wu and Z. Zhang, Only-train-electrical-to-optical-conversion (OTEOC): Simple diffractive neural networks with optical readout, Opt. Express 30, 28024 (2022).
  50. E. Bolduc, N. Bent, E. Santamato, E. Karimi, and R. W. Boyd, Exact solution to simultaneous intensity and phase encryption with a single phase-only hologram, Opt. Lett. 38, 3546 (2013).
  51. D. Ancora, M. Negri, A. Gianfrate, D. Trypogeorgos, L. Dominici, D. Sanvitto, F. Ricci-Tersenghi, and L. Leuzzi, Multi-mode fiber reservoir computing overcomes shallow neural networks classifiers, arXiv preprint arXiv:2210.04745.
  52. (https://www.kaggle.com/datasets/rodolfomendes/abalone-dataset).
  53. (https://www.kaggle.com/datasets/hojjatk/mnist-dataset).

Outline

Information

Phys. Rev. Applied 22, 034041– Published 17 September, 2024
  • Received 3 April 2024
  • Revised 6 June 2024
  • Accepted 30 August 2024
Crossmark - Check for updates button

© 2024 American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation