Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Thermal Crosstalk Modelling and Compensation Methods for Programmable Photonic Integrated Circuits (2404.10589v1)

Published 19 Mar 2024 in cs.ET, cs.LG, and physics.optics

Abstract: Photonic integrated circuits play an important role in the field of optical computing, promising faster and more energy-efficient operations compared to their digital counterparts. This advantage stems from the inherent suitability of optical signals to carry out matrix multiplication. However, even deterministic phenomena such as thermal crosstalk make precise programming of photonic chips a challenging task. Here, we train and experimentally evaluate three models incorporating varying degrees of physics intuition to predict the effect of thermal crosstalk in different locations of an integrated programmable photonic mesh. We quantify the effect of thermal crosstalk by the resonance wavelength shift in the power spectrum of a microring resonator implemented in the chip, achieving modelling errors <0.5 pm. We experimentally validate the models through compensation of the crosstalk-induced wavelength shift. Finally, we evaluate the generalization capabilities of one of the models by employing it to predict and compensate for the effect of thermal crosstalk for parts of the chip it was not trained on, revealing root-mean-square-errors of <2.0 pm.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. J. D. Armitage and A. W. Lohmann, “Character Recognition by Incoherent Spatial Filtering,” Appl. Opt., vol. 4, no. 4, pp. 461–467, Apr. 1965.
  2. N. H. Farhat, D. Psaltis, A. Prata, and E. Paek, “Optical implementation of the Hopfield model,” Appl. Opt., vol. 24, no. 10, pp. 1469–1475, May 1985.
  3. P. L. McMahon, “The physics of optical computing,” Nature Reviews Physics, vol. 5, no. 12, pp. 717–734, Dec. 2023.
  4. Y. Shen, N. C. Harris, S. Skirlo, M. Prabhu, T. Baehr-Jones, M. Hochberg, X. Sun, S. Zhao, H. Larochelle, D. Englund, and M. Soljačić, “Deep learning with coherent nanophotonic circuits,” Nature Photonics, vol. 11, no. 7, pp. 441–446, Jul. 2017.
  5. L. De Marinis, M. Cococcioni, O. Liboiron-Ladouceur, G. Contestabile, P. Castoldi, and N. Andriolli, “Photonic Integrated Reconfigurable Linear Processors as Neural Network Accelerators,” Applied Sciences, vol. 11, no. 13, 2021.
  6. A. N. Tait, T. F. de Lima, E. Zhou, A. X. Wu, M. A. Nahmias, B. J. Shastri, and P. R. Prucnal, “Neuromorphic photonic networks using silicon photonic weight banks,” Scientific Reports, vol. 7, no. 1, p. 7430, Aug. 2017.
  7. F. Ashtiani, A. J. Geers, and F. Aflatouni, “An on-chip photonic deep neural network for image classification,” Nature, vol. 606, no. 7914, pp. 501–506, Jun. 2022.
  8. W. Zhang, C. Huang, H.-T. Peng, S. Bilodeau, A. Jha, E. Blow, T. F. d. Lima, B. J. Shastri, and P. Prucnal, “Silicon microring synapses enable photonic deep learning beyond 9-bit precision,” Optica, vol. 9, no. 5, pp. 579–584, May 2022.
  9. B. Shi, N. Calabretta, and R. Stabile, “InP photonic integrated multi-layer neural networks: Architecture and performance analysis,” APL Photonics, vol. 7, no. 1, p. 010801, Jan. 2022.
  10. N. Youngblood, “Coherent Photonic Crossbar Arrays for Large-Scale Matrix-Matrix Multiplication,” IEEE Journal of Selected Topics in Quantum Electronics, vol. 29, no. 2: Optical Computing, pp. 1–11, 2023.
  11. E. A. Vlieg, L. Talandier, R. Dangel, F. Horst, and B. J. Offrein, “An Integrated Photorefractive Analog Matrix-Vector Multiplier for Machine Learning,” Applied Sciences, vol. 12, no. 9, 2022.
  12. S. Banerjee, M. Nikdast, and K. Chakrabarty, “Modeling Silicon-Photonic Neural Networks under Uncertainties,” in 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), 2021, pp. 98–101.
  13. D. Pérez, I. Gasulla, L. Crudgington, D. J. Thomson, A. Z. Khokhar, K. Li, W. Cao, G. Z. Mashanovich, and J. Capmany, “Multipurpose silicon photonics signal processor core,” Nature Communications, vol. 8, no. 1, p. 636, Sep. 2017.
  14. M. Y.-S. Fang, S. Manipatruni, C. Wierzynski, A. Khosrowshahi, and M. R. DeWeese, “Design of optical neural networks with component imprecisions,” Opt. Express, vol. 27, no. 10, pp. 14 009–14 029, May 2019.
  15. S. Bandyopadhyay, R. Hamerly, and D. Englund, “Hardware error correction for programmable photonics,” Optica, vol. 8, no. 10, pp. 1247–1255, Oct. 2021.
  16. A. Cem, S. Yan, Y. Ding, D. Zibar, and F. D. Ros, “Data-Driven Modeling of Mach-Zehnder Interferometer-Based Optical Matrix Multipliers,” Journal of Lightwave Technology, vol. 41, no. 16, pp. 5425–5436, 2023.
  17. S. Biasi, R. Franchi, D. Bazzanella, and L. Pavesi, “On the effect of the thermal cross-talk in a photonic feed-forward neural network based on silicon microresonators,” Frontiers in Physics, vol. 10, 2022.
  18. S. M. Buckley, A. N. Tait, A. N. McCaughan, and B. J. Shastri, “Photonic online learning: a perspective,” Nanophotonics, vol. 12, no. 5, pp. 833–845, 2023.
  19. F. Brückerhoff-Plückelmann, I. Bente, D. Wendland, J. Feldmann, C. D. Wright, H. Bhaskaran, and W. Pernice, “A large scale photonic matrix processor enabled by charge accumulation,” Nanophotonics, vol. 12, no. 5, pp. 819–825, 2023.
  20. A. Cem, D. Sanchez-Jacome, D. Pérez-López, and F. Da Ros, “Thermal crosstalk modeling and compensation for programmable photonic processors,” in 2023 IEEE Photonics Conference (IPC), 2023, pp. 1–2.
  21. T. W. Hughes, M. Minkov, Y. Shi, and S. Fan, “Training of photonic neural networks through in situ backpropagation and gradient measurement,” Optica, vol. 5, no. 7, pp. 864–871, Jul. 2018.
  22. J. Gu, C. Feng, H. Zhu, R. T. Chen, and D. Z. Pan, “Light in AI: Toward Efficient Neurocomputing With Optical Neural Networks—A Tutorial,” IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 69, no. 6, pp. 2581–2585, 2022.
  23. L. G. Wright, T. Onodera, M. M. Stein, T. Wang, D. T. Schachter, Z. Hu, and P. L. McMahon, “Deep physical neural networks trained with backpropagation,” Nature, vol. 601, no. 7894, pp. 549–555, Jan. 2022.
  24. S. Pai, Z. Sun, T. W. Hughes, T. Park, B. Bartlett, I. A. D. Williamson, M. Minkov, M. Milanizadeh, N. Abebe, F. Morichetti, A. Melloni, S. Fan, O. Solgaard, and D. A. B. Miller, “Experimentally realized in situ backpropagation for deep learning in photonic neural networks,” Science, vol. 380, no. 6643, pp. 398–404, 2023.
  25. Y. Bengio, D.-H. Lee, J. Bornschein, and Z. Lin, “Towards Biologically Plausible Deep Learning,” ArXiv, vol. abs/1502.04156, 2015.
  26. A. Nøkland, “Direct feedback alignment provides learning in deep neural networks,” in Neural Information Processing Systems, 2016.
  27. G. Hinton, “The forward-forward algorithm: Some preliminary investigations,” 2022.
  28. M. J. Filipovich, Z. Guo, M. Al-Qadasi, B. A. Marquez, H. D. Morison, V. J. Sorger, P. R. Prucnal, S. Shekhar, and B. J. Shastri, “Silicon photonic architecture for training deep neural networks with direct feedback alignment,” Optica, vol. 9, no. 12, pp. 1323–1332, Dec. 2022.
  29. A. Momeni, B. Rahmani, M. Malléjac, P. d. Hougne, and R. Fleury, “Backpropagation-free training of deep physical neural networks,” Science, vol. 382, no. 6676, pp. 1297–1303, 2023.
  30. I. Oguz, J. Ke, Q. Weng, F. Yang, M. Yildirim, N. U. Dinc, J.-L. Hsieh, C. Moser, and D. Psaltis, “Forward–forward training of an optical neural network,” Opt. Lett., vol. 48, no. 20, pp. 5249–5252, Oct. 2023.
  31. S. Buckley and A. McCaughan, “A general approach to fast online training of modern datasets on real neuromorphic systems without backpropagation,” 2022.
  32. R. Shao, G. Zhang, and X. Gong, “Generalized robust training scheme using genetic algorithm for optical neural networks with imprecise components,” Photon. Res., vol. 10, no. 8, pp. 1868–1876, Aug. 2022.
  33. M. Moralis-Pegios, G. Mourgias-Alexandris, A. Tsakyridis, G. Giamougiannis, A. Totovic, G. Dabos, N. Passalis, M. Kirtas, T. Rutirawut, F. Y. Gardes, A. Tefas, and N. Pleros, “Neuromorphic Silicon Photonics and Hardware-Aware Deep Learning for High-Speed Inference,” Journal of Lightwave Technology, vol. 40, no. 10, pp. 3243–3254, 2022.
  34. V. Shah and N. Youngblood, “AnalogVNN: A fully modular framework for modeling and optimizing photonic neural networks,” APL Machine Learning, vol. 1, no. 2, p. 026116, Jun. 2023.
  35. G. Sarantoglou, A. Bogris, C. Mesaritakis, and S. Theodoridis, “Bayesian photonic accelerators for energy efficient and noise robust neural processing,” IEEE Journal of Selected Topics in Quantum Electronics, vol. 28, no. 6, p. 1–10, Nov. 2022.
  36. K. Lu and X. Guo, “Efficient training of unitary optical neural networks,” Opt. Express, vol. 31, no. 24, pp. 39 616–39 623, Nov. 2023.
  37. D. Pérez-López, A. Gutierrez, D. Sánchez, A. López-Hernández, M. Gutierrez, E. Sánchez-Gomáriz, J. Fernández, A. Cruz, A. Quirós, Z. Xie, J. Benitez, N. Bekesi, A. Santomé, D. Pérez-Galacho, P. DasMahapatra, A. Macho, and J. Capmany, “General-purpose programmable photonic processor for advanced radiofrequency applications,” Nature Communications, vol. 15, no. 1, p. 1563, Feb. 2024.
  38. W. Bogaerts, P. De Heyn, T. Van Vaerenbergh, K. De Vos, S. Kumar Selvaraja, T. Claes, P. Dumon, P. Bienstman, D. Van Thourhout, and R. Baets, “Silicon microring resonators,” Laser & Photonics Reviews, vol. 6, no. 1, pp. 47–73, 2012.
  39. M. Jacques, A. Samani, E. El-Fiky, D. Patel, Z. Xing, and D. V. Plant, “Optimization of thermo-optic phase-shifter design and mitigation of thermal crosstalk on the SOI platform,” Opt. Express, vol. 27, no. 8, pp. 10 456–10 471, Apr. 2019.
  40. J. Lydiate, “Modelling and simulation of a thermally induced optical transparency in a dual micro-ring resonator,” Royal Society Open Science, vol. 4, no. 7, p. 170381, 2017.
  41. K. Padmaraju and K. Bergman, “Resolving the thermal challenges for silicon microring resonator devices,” Nanophotonics, vol. 3, no. 4-5, pp. 269–281, 2014.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now