Skip to main content
SpringerLink
Log in

Supervised Learning Strategy for Spiking Neurons Based on Their Segmental Running Characteristics

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

Supervised learning of spiking neurons is an effective simulation method to explore the learning mechanism of real neurons. Desired output spike trains are often used as supervised signals to control the synaptic strength adjustment of neurons for precise emission. The goal of supervised learning is also to allow spiking neurons to enter the desired running and firing state. The running process of a spiking neuron is a continuous process, but because of absolute refractory periods, it is regarded as several running segments. Based on the segmental characteristic, a new supervised learning strategy for spiking neurons is proposed to expand the action mode of supervised signals in supervised learning. Desired output spikes are used to actively regulate the running segments and make them more efficient in achieving the desired running and firing state. Supervised signals actively regulate the running process of neurons and are more comprehensively involved in the learning process than simply participating in adjusting synaptic weights. Based on two weight adjustment mechanisms of spiking neurons, two new specific supervised learning methods are proposed. The experimental results obtained using various settings indicate that the two learning methods have higher learning performance, which indicates the effectiveness of the new learning strategy.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

References

  1. Bose NK, Liang P (1996) Neural network fundamentals with graphs, algorithms and applications. McGraw-Hill, New York

    MATH  Google Scholar 

  2. Gerstner W, Kistler WM (2002) Spiking neuron models. Single neurons, populations, plasticity. Cambridge University Press, New York

    MATH  Google Scholar 

  3. Maass W (1997) Networks of spiking neurons: The third generation of neural network models. Neural Netw 10(9):1659–1671

    Google Scholar 

  4. Nazari S, Faez K (2019) Establishing the flow of information between two bio-inspired spiking neural networks. Inf Sci 477:80–99

    Google Scholar 

  5. Zhang A, Niu Y, Gao Y et al (2022) Second-order information bottleneck based spiking neural networks for semg recognition. Inf Sci 585:543–558

    Google Scholar 

  6. Beer M, Urenda J, Kosheleva O, et al (2020) Why spiking neural networks are efficient: a theoreme. In: Lesot MJ, Vieira S, Reformat MZ (eds) 18th International conference on information processing and management of uncertainty in knowledge-based systems, CCIS, vol 1237. Springer, pp 59–69

  7. Roy K, Jaiswal A, Panda P (2019) Towards spike-based machine intelligence with neuromorphic computing. Nature 575:607–617

    Google Scholar 

  8. Tavanaei A, Ghodrati M, Kheradpisheh SR et al (2019) Deep learning in spiking neural networks. Neural Netw 111:47–63

    Google Scholar 

  9. Kumarasinghe K, Kasabov N, Taylor D (2020) Deep learning and deep knowledge representation in spiking neural networks for brain-computer interfaces. Neural Netw 121:169–185

    Google Scholar 

  10. Nazari S, Faez K (2019) Novel systematic mathematical computation based on the spiking frequency gate (sfg): innovative organization of spiking computer. Inf Sci 474:221–235

    MathSciNet  MATH  Google Scholar 

  11. Nandakumar SR, Boybat I, Gallo ML et al (2020) Experimental demonstration of supervised learning in spiking neural networks with phase-change memory synapses. Sci Rep 10(1):1. https://doi.org/10.1038/s41598-020-64878-5

    Article  Google Scholar 

  12. Abusnaina AA, Abdullah R, Kattan A (2019) Supervised training of spiking neural network by adapting the e-mwo algorithm for pattern classification. Neural Process Lett 49:661–682

    Google Scholar 

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

    Google Scholar 

  14. Bohte SM, Kok JN, La Poutré JA (2002) Error-backpropagation in temporally encoded networks of spiking neurons. Neurocomputing 48(1–4):17–37

    MATH  Google Scholar 

  15. Ponulak F (2005) Resume-new supervised learning method for spiking neural networks. Institute of Control and Information Engineering, Poznan University of Technology, Tech. rep

  16. de Kamps M, van der Velde F (2002) Implementation of multilayer perceptron networks by populations of spiking neurons using rate coding. Neurocomputing 44–46:353–358

    MATH  Google Scholar 

  17. Gütig R (2016) Spiking neurons can discover predictive features by aggregate-label learning. Science 351:6277

    Google Scholar 

  18. Xu Y, Zeng X, Han L et al (2013) A supervised multi-spike learning algorithm based on gradient descent for spiking neural networks. Neural Netw 43:99–113

    MATH  Google Scholar 

  19. Taherkhani A, Belatreche A, Li Y et al (2018) A supervised learning algorithm for learning precise timing of multiple spikes in multilayer spiking neural networks. IEEE Trans Neural Networks Learn Syst 29(11):5394–5407

    MathSciNet  Google Scholar 

  20. Sengupta N, Kasabov N (2017) Spike-time encoding as a data compression technique for pattern recognition of temporal data. Inf Sci 406–407:133–145

    Google Scholar 

  21. Gütig R (2014) To spike, or when to spike? Neurobiology 25:134–139

    Google Scholar 

  22. Wang X, Lin X, Dang X (2020) Supervised learning in spiking neural networks: a review of algorithms and evaluations. Neural Netw 125:258–280

    Google Scholar 

  23. Xu Y, Yang J, Zhong S (2017) An online supervised learning method based on gradient descent for spiking neurons. Neural Netw 93:7–20

    MATH  Google Scholar 

  24. Florian RV (2012) The chronotron: a neuron that learns to fire temporally precise spike patterns. PLoS ONE 7(e40):233. https://doi.org/10.1371/journal.pone.0040233

    Article  Google Scholar 

  25. Victor JD, Purpura KP (1996) Nature and precision of temporal coding in the visual cortex: a metric-space analysis. J Neurophysiol 76(6):1310–1326

    Google Scholar 

  26. Ponulak F, Kasiński A (2010) Supervised learning in spiking neural networks with resume: sequence learning, classification and spike-shifting. Neural Comput 22(2):467–510

    MathSciNet  MATH  Google Scholar 

  27. Markram H, Lübke J, Frotscher M et al (1997) Regulation of synaptic efficacy by coincidence of postsynaptic aps and epsps. Science 275:213–215

    Google Scholar 

  28. Bi GQ, Poo MM (1998) Synaptic modifications in cultured hippocampal neurons: dependence on spike timing, synaptic strength, and postsynaptic cell type. J Neurosci 18(24):10464–10472

    Google Scholar 

  29. Yu Q, Tang H, Tan KC et al (2013) Precise-spike-driven synaptic plasticity: learning hetero-association of spatiotemporal spike patterns. PLoS ONE 8(e78):318. https://doi.org/10.1371/journal.pone.0078318

    Article  Google Scholar 

  30. Mohemmed A, Schliebs S (2012) Span: spike pattern association neuron for learning spatio-temoral spike patterns. Int J Neural Syst 22(1250):012. https://doi.org/10.1142/S0129065712500128

    Article  Google Scholar 

  31. Mohemmed A, Schliebs S, Matsuda S et al (2013) Training spiking neural networks to associate spatio-temporal input-output spike patterns. Neurocomputing 107:3–10

    Google Scholar 

  32. Gardner B, Sporea I, Grüning A (2015) Learning spatiotemporally encoded pattern transformations in structured spiking neural networks. Neural Comput 27(12):2548–2586

    MathSciNet  MATH  Google Scholar 

  33. Lin X, Zhang N, Wang X (2015) An online supervised learning algorithm based on nonlinear spike train kernels. In: Huang DS, Bevilacqua V, Premaratne P (eds) International conference on intelligent computing, vol LNCS 9225. Springer, pp 106–115

  34. Xu Y, Zeng X, Zhong S (2013) A new supervised learning algorithm for spiking neurons. Neural Comput 25:1472–1511

    MathSciNet  MATH  Google Scholar 

  35. Minsky M, Papert S (1969) Perceptrons. MIT Press, Cambridge, MA

    MATH  Google Scholar 

  36. Qu H, Xie X, Liu Y et al (2015) Improved perception-based spiking neuron learning rule for real-time user authentication. Neurocomputing 151:310–318

    Google Scholar 

  37. Xie X, Qu H, Liu G et al (2017) Efficient training of supervised spiking neural networks via the normalized perceptron based learning rule. Neurocomputing 241:152–163

    Google Scholar 

  38. Memmesheimer RM, Rubin R, Ölveczky BP et al (2014) Learning precisely timed spikes. Neuron 82:1–14

    Google Scholar 

  39. Luo X, Qu H, Zhang Y et al (2019) First error-based supervised learning algorithm for spiking neural networks. Front Neurosci 13:559

    Google Scholar 

  40. Zenke F, Ganguli S (2018) Superspike: supervised learning in multilayer spiking neural networks. Neural Comput 30(6):1514–1541

    MathSciNet  MATH  Google Scholar 

  41. van Rossum MC, O’Brien BJ, Smith RG (2003) Effects of noise on the spike timing precision of retinal ganglion cells. J Neurophysiol 89:2406–2419

    Google Scholar 

  42. Taherkhani A, Belatreche A, Li Y et al (2015) Dl-resume: A delay learning-based remote supervised method for spiking neurons. IEEE Trans Neural Networks Learn Syst 26(12):3137–3149

    MathSciNet  Google Scholar 

  43. Zhang M, Wu J, Belatreche A et al (2020) Supervised learning in spiking neural networks with synaptic delay-weight plasticity. Neurocomputing 409:103–118

    Google Scholar 

  44. Zhang M, Qu H, Xie X et al (2017) Supervised learning in spiking neural networks with noise-threshold. Neurocomputing 219:333–349

    Google Scholar 

  45. Xu Y, Yang J, Zeng X (2019) An optimal time interval of input spikes involved in synaptic adjustment of spike sequence learning. Neural Netw 116:11–24

    Google Scholar 

  46. Kim J, Kim CH, Woo SY et al (2020) Initial synaptic weight distribution for fast learning speed and high recognition rate in stdp-based spiking neural network. Solid State Electron 165(107):742. https://doi.org/10.1016/j.sse.2019.107742

    Article  Google Scholar 

  47. Zhang M, Qu H, Belatreche A et al (2018) Empd: an efficient membrane potential driven supervised learning algorithm for spiking neurons. IEEE Trans Cognit Dev Syst 10(2):151–162

    Google Scholar 

  48. Zhang M, Qu H, Belatreche A et al (2019) A highly effective and robust membrane potential-driven supervised learning method for spiking neurons. IEEE Transactions on Neural Networks and Learning Systems 30(1):123–137

    Google Scholar 

  49. Zhang Y, Qu H, Luo X et al (2021) A new recursive least squares-based learning algorithm for spiking neurons. Neural Netw 138:110–125

    Google Scholar 

  50. Yu Q, Li H, Tan KC (2019) Spike timing or rate? Neurons learn to make decisions for both through threshold-driven plasticity. IEEE Trans Cybern 49(6):2178–2189

    Google Scholar 

  51. Zhang M, Luo X, Chen Y et al (2020) An efficient threshold-driven aggregate-label learning algorithm for multimodal information processing. IEEE J Sel Top Signal Process 14(3):592–602

    Google Scholar 

  52. Kandel ER, Schwartz JH, Jessell TM (2000) Principles of neural science. McGraw- Hill, New York

    Google Scholar 

  53. Gerstner W (1995) Time structure of the activity in neural network models. Phys Rev E 51:738–758

    Google Scholar 

  54. Ghosh-Dastidar S, Adeli H (2009) A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection. Neural Netw 22:1419–1431

    Google Scholar 

  55. Schreiber S, Fellous JM, Whitmer D et al (2003) A new correlation-based measure of spike timing reliability. Neurocomputing 52–54:925–931

    Google Scholar 

  56. Schneidman E (2001) Noise and information in neural codes. PhD thesis, The Hebrew University, Institute of Computer Science, Jerusalem, Israel

  57. Yu Q, Tang H, Tan KC et al (2014) A brain-inspired spiking neural network model with temporal encoding and learning. Neurocomputing 138:3–13

    Google Scholar 

  58. Wang J, Belatreche A, Maguire L et al (2014) An online supervised learning method for spiking neural networks with adaptive structure. Neurocomputing 144:526–536

    Google Scholar 

  59. Lin X, Zhang M, Wang X (2021) Supervised learning algorithm for multilayer spiking neural networks with long-term memory spike response model. Comput Intell Neurosci 2021:8592824:1-8592824:16. https://doi.org/10.1155/2021/8592824

  60. Sporea I, Grüning A (2013) Supervised learning in multilayer spiking neural networks. Neural Comput 25(2):473–509

    MathSciNet  MATH  Google Scholar 

  61. Hu T, Lin X, Wang X et al (2022) Supervised learning algorithm based on spike optimization mechanism for multilayer spiking neural networks. Int J Mach Learn Cybern 13(7):1981–1995. https://doi.org/10.1007/s13042-021-01500-8

    Article  Google Scholar 

Download references

Acknowledgements

This work is supported by the National Natural Science Foundation of China under grant 31872847 and the Key Research and Development Plan of Jiangsu Province of China under grant BE2021358 (Modern Agriculture).

Author information

Authors and Affiliations

  1. College of Artificial Intelligence, Nanjing Agricultural University, Nanjing, 210095, Jiangsu, China

    Xingjian Gu, Xin Shu, Yan Xu & Haiyan Jiang

  2. School of Management, Zhuhai Campus, Beijing Normal University, Zhuhai, 519087, Guangdong, China

    Jing Yang

  3. School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, 210094, Jiangsu, China

    Xiangbo Shu

Authors
  1. Xingjian Gu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xin Shu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jing Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yan Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Haiyan Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Xiangbo Shu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yan Xu.

Ethics declarations

Competing Interests

The authors declare that they have no competing of interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Gu, X., Shu, X., Yang, J. et al. Supervised Learning Strategy for Spiking Neurons Based on Their Segmental Running Characteristics. Neural Process Lett 55, 10747–10772 (2023). https://doi.org/10.1007/s11063-023-11348-4

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-023-11348-4

Keywords

Search

Navigation