Movatterモバイル変換

[0]ホーム
URL:

Skip to main content
Springer Nature Link
Log in

Conversion of a single-layer ANN to photonic SNN for pattern recognition

  • Research Paper
  • Published:
Science China Information Sciences Aims and scope Submit manuscript

Abstract

This work presents a complete conversion scheme for photonic spiking neural networks (SNNs). We verified that the output of an artificial neural network (ANN) trained with the simulated optical activation function can be directly converted into the spike rate of a photonic spiking neuron model. To reveal the feasibility of hardware implementation, we considered the effects of different bit precisions of data and weight, noise level, and bias current mismatch on the converted results. The proposed scheme was evaluated using the Deterding vowel, IRIS, TIDIGITS, and MNIST datasets for pattern recognition, and achieved mean accuracies of 95.80%, 98.67%, 96.19%, and 92.33%, respectively. The proposed scheme can convert an ANN into a photonic SNN with almost no precision loss, and the performance was comparable to that of an ANN trained with the rectified linear unit function. The proposed scheme can enable the high-performance implementation of photonic SNNs.

This is a preview of subscription content,log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Japan)

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. Schuman C D, Potok T E, Patton R M, et al. A survey of neuromorphic computing and neural networks in hardware. 2017. ArXiv:1705.06963

  2. Zhou S B, Li X H, Chen Y, et al. Temporal-coded deep spiking neural network with easy training and robust performance. In: Proceedings of Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence, Palo Alto, 2021. 11143–11151

  3. Tavanaei A, Maida A. BP-STDP: approximating backpropagation using spike timing dependent plasticity. Neurocomputing, 2019, 330: 39–47

    Article  Google Scholar 

  4. Wu Y J, Deng L, Li G Q, et al. Spatio-temporal backpropagation for training high-performance spiking neural networks. Front Neurosci, 2018, 12: 331

    Article  Google Scholar 

  5. Bohté S M, Kok J N, Poutré H L. Error-backpropagation in temporally encoded networks of spiking neurons. Neurocomputing, 2002, 48: 17–37

    Article MATH  Google Scholar 

  6. Wu Y J, Deng L, Li G Q, et al. Direct training for spiking neural networks: faster, larger, better. In: Proceedings of Association for the Advancement of Artificial Intelligence, 2019. 1311–1318

  7. Xiang S Y, Jiang S Q, Liu X S, et al. Spiking VGG7: deep convolutional spiking neural network with direct training for object recognition. Electronics, 2022, 11: 2097

    Article  Google Scholar 

  8. Ponulak F, Kasihńki A. Supervised learning in spiking neural networks with ReSuMe: sequence learning, classification, and spike shifting. Neural Computation, 2010, 22: 467–510

    Article MathSciNet MATH  Google Scholar 

  9. Gütig R, Sompolinsky H. The Tempotron: a neuron that learns spike timing-based decisions. Nat Neurosci, 2006, 9: 420–428

    Article  Google Scholar 

  10. Han Y N, Xiang S Y, Ren Z X, et al. Delay-weight plasticity-based supervised learning in optical spiking neural networks. Photon Res, 2021, 9: B119

    Article  Google Scholar 

  11. Liu F X, Zhao W B, Chen Y B, et al. SSTDP: supervised spike timing dependent plasticity for efficient spiking neural network training. Front Neurosci, 2021, 15: 756876

    Article  Google Scholar 

  12. O’Connor P, Neil D, Liu S C, et al. Real-time classification and sensor fusion with a spiking deep belief network. Front Neurosci, 2013, 7: 178

    Google Scholar 

  13. Cao Y Q, Chen Y, Khosla D. Spiking deep convolutional neural networks for energy-efficient object recognition. Int J Comput Vis, 2015, 113: 54–66

    Article MathSciNet  Google Scholar 

  14. Rueckauer B, Lungu I A, Hu Y H, et al. Conversion of continuous-valued deep networks to efficient event-driven networks for image classification. Front Neurosci, 2017, 11: 682

    Article  Google Scholar 

  15. Ding J H, Yu Z F, Tian Y H, et al. Optimal ANN-SNN conversion for fast and accurate inference in deep spiking neural networks. In: Proceedings of the 30th International Joint Conference on Artificial Intelligence Main Track, 2021. 2328–2336

  16. Woods D, Naughton T J. Photonic neural networks. Nat Phys, 2012, 8: 257–259

    Article  Google Scholar 

  17. Yao P, Wu H Q, Gao B, et al. Face classification using electronic synapses. Nat Commun, 2017, 8: 15199

    Article  Google Scholar 

  18. Xiang S Y, Gong J K, Zhang Y H, et al. Numerical implementation of wavelength-dependent Photonic spike timing dependent plasticity based on VCSOA. IEEE J Quantum Electron, 2018, 54: 1–7

    Article  Google Scholar 

  19. Boybat I, Gallo M L, Nandakumar S R, et al. Neuromorphic computing with multi-memristive synapses. Nat Commun, 2018, 9: 2514

    Article  Google Scholar 

  20. Midya R, Wang Z R, Asapu S, et al. Artificial neural network (ANN) to spiking neural network (SNN) converters based on diffusive memristors. Adv Electron Mater, 2019, 5: 1900060

    Article  Google Scholar 

  21. Feldmann J, Youngblood N, Wright C D, et al. All-optical spiking neurosynaptic networks with self-learning capabilities. Nature, 2019, 569: 208–214

    Article  Google Scholar 

  22. Zhang J Y, Dai S L, Zhao Y W, et al. Recent progress in photonic synapses for neuromorphic systems. Adv Intell Syst, 2020, 2: 1900136

    Article  Google Scholar 

  23. Xiang S Y, Han Y N, Song Z W, et al. A review: photonics devices, architectures, and algorithms for optical neural computing. J Semicond, 2021, 42: 023105

    Article  Google Scholar 

  24. Xiang J L, Zhang Y J, Zhao Y T, et al. All-optical silicon microring spiking neuron. Photon Res, 2022, 10: 939

    Article  Google Scholar 

  25. Xiang S Y, Shi Y C, Guo X X, et al. Hardware-algorithm collaborative computing with photonic spiking neuron chip based on an integrated Fabry-Perot laser with a saturable absorber. Optica, 2023, 10: 162–171

    Article  Google Scholar 

  26. Shen Y C, Harris N C, Skirlo S, et al. Deep learning with coherent nanophotonic circuits. Nat Photon, 2017, 11: 441–446

    Article  Google Scholar 

  27. Zhao X M, Lv H B, Chen C, et al. On-chip reconfigurable optical neural networks. Research Square, 2021. doi:https://doi.org/10.21203/rs.3.rs-155560/v1

  28. Xiang S Y, Zhang H, Guo X X, et al. Cascadable neuron-like spiking dynamics in coupled VCSELs subject to orthogonally polarized optical pulse injection. IEEE J Sel Top Quantum Electron, 2017, 23: 1–7

    Article  Google Scholar 

  29. Deng T, Robertson J, Hurtado A. Controlled propagation of spiking dynamics in vertical-cavity surface-emitting lasers: towards neuromorphic photonic networks. IEEE J Sel Top Quantum Electron, 2017, 23: 1–8

    Google Scholar 

  30. Robertson J, Wade E, Kopp Y, et al. Toward neuromorphic photonic networks of ultrafast spiking laser neurons. IEEE J Sel Top Quantum Electron, 2020, 26: 1–15

    Article  Google Scholar 

  31. Pammi V A, Alfaro-Bittner K, Clerc M G, et al. Photonic computing with single and coupled spiking micropillar lasers. IEEE J Sel Top Quantum Electron, 2020, 26: 1–7

    Article  Google Scholar 

  32. Chlouverakis K E, Adams M J. Two-section semiconductor lasers subject to optical injection. IEEE J Sel Top Quantum Electron, 2004, 10: 982–990

    Article  Google Scholar 

  33. Nahmias M A, Shastri B J, Tait A N, et al. A leaky integrate-and-fire laser neuron for ultrafast cognitive computing. IEEE J Sel Top Quantum Electron, 2013, 19: 1–12

    Article  Google Scholar 

  34. Dubbeldam J L A, Krauskopf B. Self-pulsations of lasers with saturable absorber: dynamics and bifurcations. Optics Commun, 1999, 159: 325–338

    Article  Google Scholar 

  35. Han Y N, Xiang S Y, Zhang Y N, et al. An all-MRR-based photonic spiking neural network for spike sequence learning. Photonics, 2022, 9: 120

    Article  Google Scholar 

  36. Xiang J L, Torchy A, Guo X H, et al. All-optical spiking neuron based on passive microresonator. J Lightwave Technol, 2020, 38: 4019–4029

    Article  Google Scholar 

  37. Chakraborty I, Saha G, Sengupta A, et al. Toward fast neural computing using all-photonic phase change spiking neurons. Sci Rep, 2018, 8: 12980

    Article  Google Scholar 

  38. Xiang S Y, Zhang Y H, Gong J K, et al. STDP-based unsupervised spike pattern learning in a photonic spiking neural network with VCSELs and VCSOAs. IEEE J Sel Top Quantum Electron, 2019, 25: 1–9

    Article  Google Scholar 

  39. Xiang S Y, Ren Z X, Song Z W, et al. Computing primitive of fully VCSEL-based all-optical spiking neural network for supervised learning and pattern classification. IEEE Trans Neural Netw Learn Syst, 2021, 32: 2494–2505

    Article  Google Scholar 

  40. Fu C T, Xiang S Y, Han Y N, et al. Multilayer photonic spiking neural networks: generalized supervised learning algorithm and network optimization. Photonics, 2022, 9: 217

    Article  Google Scholar 

  41. Han Y N, Xiang S Y, Song Z W, et al. Spiking dynamics and synchronization properties of optical neurons based on VCSEL-SAs. Nonlinear Dyn, 2021, 105: 2665–2675

    Article  Google Scholar 

  42. Deterding D H. Speaker normalisation for automatic speech recognition. Dissertation for Ph.D. Degree. Cambridge: University of Cambridge, 1990

    Google Scholar 

  43. Leonard R G. A database for speaker-independent digit recognition. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, San Diego, 1984. 328–331

  44. Davis S, Mermelstein P. Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans Acoust Speech Signal Process, 1980, 28: 357–366

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported in part by National Key Research and Development Program of China (Grant Nos. 2021YFB2801900, 2021YFB2801901, 2021YFB2801902, 2021YFB2801904), National Natural Science Foundation of China (Grant Nos. 61974177, 61674119), National Outstanding Youth Science Fund Project of National Natural Science Foundation of China (Grant No. 62022062), and Fundamental Research Funds for the Central Universities (Grant No. JB210114).

Author information

Authors and Affiliations

  1. State Key Laboratory of Integrated Service Networks, State Key Discipline Laboratory of Wide Bandgap Semiconductor Technology, Xidian University, Xi’an, 710071, China

    Yanan Han, Shuiying Xiang, Tianrui Zhang, Yahui Zhang & Xingxing Guo

  2. Yongjiang Laboratory, Ningbo, 315202, China

    Yuechun Shi

Authors
  1. Yanan Han

    You can also search for this author inPubMed Google Scholar

  2. Shuiying Xiang

    You can also search for this author inPubMed Google Scholar

  3. Tianrui Zhang

    You can also search for this author inPubMed Google Scholar

  4. Yahui Zhang

    You can also search for this author inPubMed Google Scholar

  5. Xingxing Guo

    You can also search for this author inPubMed Google Scholar

  6. Yuechun Shi

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence toShuiying Xiang.

Rights and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Han, Y., Xiang, S., Zhang, T.et al. Conversion of a single-layer ANN to photonic SNN for pattern recognition.Sci. China Inf. Sci.67, 112403 (2024). https://doi.org/10.1007/s11432-022-3699-2

Download citation

Keywords

Access this article

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Japan)

Instant access to the full article PDF.

Advertisement

[8]ページ先頭
©2009-2025 Movatter.jp