Skip to main content

Thank you for visiting You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks

A preprint version of the article is available at bioRxiv.


Inspired by detailed modelling of biological neurons, spiking neural networks (SNNs) are investigated as biologically plausible and high-performance models of neural computation. The sparse and binary communication between spiking neurons potentially enables powerful and energy-efficient neural networks. The performance of SNNs, however, has remained lacking compared with artificial neural networks. Here we demonstrate how an activity-regularizing surrogate gradient combined with recurrent networks of tunable and adaptive spiking neurons yields the state of the art for SNNs on challenging benchmarks in the time domain, such as speech and gesture recognition. This also exceeds the performance of standard classical recurrent neural networks and approaches that of the best modern artificial neural networks. As these SNNs exhibit sparse spiking, we show that they are theoretically one to three orders of magnitude more computationally efficient compared to recurrent neural networks with similar performance. Together, this positions SNNs as an attractive solution for AI hardware implementations.

This is a preview of subscription content, access via your institution

Access options

Rent or buy this article

Get just this article for as long as you need it


Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Illustration of processing and learning in networks of spiking neurons.
Fig. 2: Complexity calculation.
Fig. 3: Details of task performance.
Fig. 4: Learning trade-offs and classification latency.

Data availability

The data analysed during this study are open source and publicly available. The dataset for ECG streaming dataset is derived from original QTDB dataset ( Spiking datasets (SHD and SSC) belong to Spiking Heidelberg Datasets, which are available at The MNIST dataset can be downloaded from The Soli dataset can be downloaded at TIMIT Acoustic-Phonetic Continuous Speech Corpus are available on request via Further information can be found in our repository (see the Code Availability section). Source data are provided with this paper.

Code availability

The code used in the study is publicly available from the GitHub repository (


  1. Hassabis, D., Kumaran, D., Summerfield, C. & Botvinick, M. Neuroscience-inspired artificial intelligence. Neuron 95, 245–258 (2017).

    Article  Google Scholar 

  2. Maass, W. Networks of spiking neurons: the third generation of neural network models. Neural Netw. 10, 1659–1671 (1997).

    Article  Google Scholar 

  3. Gerstner, W., Kempter, R., Van Hemmen, J. L. & Wagner, H. A neuronal learning rule for sub-millisecond temporal coding. Nature 383, 76–78 (1996).

    Article  Google Scholar 

  4. Davies, M. et al. Loihi: a neuromorphic manycore processor with on-chip learning. IEEE Micro 38, 82–99 (2018).

    Article  Google Scholar 

  5. Bohte, S. M., Kok, J. N. & La Poutré, J. A. SpikeProp: backpropagation for networks of spiking neurons. In European Symposium on Artificial Neural Networks (ESANN) Vol. 48, 17–37 (ESANN, 2000).

  6. Shrestha, S. B. & Orchard, G. Slayer: spike layer error reassignment in time. In Advances in Neural Information Processing Systems Vol. 31, 1412–1421 (NeurIPS, 2018).

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

    Article  MathSciNet  Google Scholar 

  8. Kheradpisheh, S. R., Ganjtabesh, M., Thorpe, S. J. & Masquelier, T. STDP-based spiking deep convolutional neural networks for object recognition. Neural Netw. 99, 56–67 (2018).

    Article  Google Scholar 

  9. Falez, P., Tirilly, P., Bilasco, I. M., Devienne, P. & Boulet, P. Multi-layered spiking neural network with target timestamp threshold adaptation and STDP. In International Joint Conference on Neural Networks (IJCNN) 1–8 (IEEE, 2019).

  10. Neftci, E. O., Mostafa, H. & Zenke, F. Surrogate gradient learning in spiking neural networks. IEEE Signal Process. Mag. 36, 61–63 (2019).

    Article  Google Scholar 

  11. Wunderlich, T. C. & Pehle, C. Event-based backpropagation can compute exact gradients for spiking neural networks. Sci. Rep. 11, 12829 (2021).

    Article  Google Scholar 

  12. Bellec, G. et al. A solution to the learning dilemma for recurrent networks of spiking neurons. Nat. Commun. 11, 1–15 (2020).

    Article  Google Scholar 

  13. Sengupta, A., Ye, Y., Wang, R., Liu, C. & Roy, K. Going deeper in spiking neural networks: VGG and residual architectures. Front. Neurosci. 13, 95 (2019).

    Article  Google Scholar 

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

    Article  Google Scholar 

  15. Yin, B., Corradi, F. & Bohté, S. M. Effective and efficient computation with multiple-timescale spiking recurrent neural networks. In International Conference on Neuromorphic Systems 2020 1–8 (ACM, 2020).

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

    Article  Google Scholar 

  17. Elfwing, S., Uchibe, E. & Doya, K. Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Netw. 107, 3–11 (2018).

    Article  Google Scholar 

  18. Elfwing, S., Uchibe, E. & Doya, K. Expected energy-based restricted boltzmann machine for classification. Neural Netw. 64, 29–38 (2015).

    Article  Google Scholar 

  19. Gerstner, W. & Kistler, W. M. Spiking Neuron Models: Single Neurons, Populations, Plasticity (Cambridge Univ. Press, 2002).

  20. Izhikevich, E. M. Simple model of spiking neurons. IEEE Trans. Neural Netw. 14, 1569–1572 (2003).

    Article  Google Scholar 

  21. Bellec, G., Salaj, D., Subramoney, A., Legenstein, R. & Maass, W. Long short-term memory and learning-to-learn in networks of spiking neurons. In Advances in Neural Information Processing Systems 787–797 (NeurIPS, 2018).

  22. Bohte, S. M. Error-backpropagation in networks of fractionally predictive spiking neurons. In International Conference on Artificial Neural Networks (ICANN) 60–68 (Springer, 2011).

  23. Wong, A., Famouri, M., Pavlova, M. & Surana, S. Tinyspeech: attention condensers for deep speech recognition neural networks on edge devices. Preprint at (2020).

  24. Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9, 1735–1780 (1997).

    Article  Google Scholar 

  25. Horowitz, M. 1.1 Computing’s energy problem (and what we can do about it). In 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC) 10–14 (IEEE, 2014).

  26. Ludgate, P. E. On a proposed analytical machine. In The Origins of Digital Computers 73–87 (Springer, 1982).

  27. Shewalkar, A., Nyavanandi, D. & Ludwig, S. A. Performance evaluation of deep neural networks applied to speech recognition: RNN, lSTM and GRU. J. Artif. Intell. Soft Comput. Res. 9, 235–245 (2019).

    Article  Google Scholar 

  28. Laguna, P., Mark, R. G., Goldberg, A. & Moody, G. B. A database for evaluation of algorithms for measurement of QT and other waveform intervals in the ECG. In Computers in Cardiology 1997 673–676 (IEEE, 1997).

  29. Cramer, B., Stradmann, Y., Schemmel, J. & Zenke, F. The Heidelberg spiking data sets for the systematic evaluation of spiking neural networks. IEEE Transactions on Neural Networks and Learning Systems 1–14 (IEEE, 2020);

  30. Wang, S., Song, J., Lien, J., Poupyrev, I. & Hilliges, O. Interacting with Soli: exploring fine-grained dynamic gesture recognition in the radio-frequency spectrum. In Proc. 29th Annual Symposium on User Interface Software and Technology 851–860 (ACM, 2016).

  31. Warden, P. Speech commands: a dataset for limited-vocabulary speech recognition. Preprint at (2018).

  32. Garofolo, J. S. TIMIT Acoustic Phonetic Continuous Speech Corpus (Linguistic Data Consortium, 1993).

  33. Pellegrini, T., Zimmer, R. & Masquelier, T. Low-activity supervised convolutional spiking neural networks applied to speech commands recognition. In 2021 IEEE Spoken Language Technology Workshop (SLT) 97–103 (IEEE, 2021).

  34. Kundu, S., Datta, G., Pedram, M. & Beerel, P. A. Spike-thrift: Towards energy-efficient deep spiking neural networks by limiting spiking activity via attention-guided compression. In Proc. IEEE/CVF Winter Conference on Applications of Computer Vision 3953–3962 (IEEE, 2021).

  35. Fang, W. et al. Incorporating learnable membrane time constant to enhance learning of spiking neural networks. Preprint at (2020).

  36. Amir, A. et al. A low power, fully event-based gesture recognition system. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 7243–7252 (IEEE, 2017).

  37. Paszke, A. et al. Pytorch: an imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems Vol. 32, 8024–8035 (NeurIPS, 2019).

  38. Zenke, F. et al. Visualizing a joint future of neuroscience and neuromorphic engineering. Neuron 109, 571–575 (2021).

    Article  Google Scholar 

  39. Zenke, F. & Neftci, E. O. Brain-inspired learning on neuromorphic substrates. Proc. IEEE Vol. 109, 1–16 (IEEE, 2021).

  40. Keijser, J. & Sprekeler, H. Interneuron diversity is required for compartment-specific feedback inhibition. Preprint at (2020).

  41. Kingma, D. P. & Ba, J. Adam: a method for stochastic optimization. In 3rd International Conference on Learning Representations (DBLP, 2015).

  42. Lichtsteiner, P., Posch, C. & Delbruck, T. A 128 × 128 120 db 15 μs latency asynchronous temporal contrast vision sensor. IEEE J. Solid-State Circuits 43, 566–576 (2008).

    Article  Google Scholar 

  43. McFee, B. et al. librosa: audio and music signal analysis in Python. In Proc.14th Python in Science Conference Vol. 8, 18–25 (SciPy, 2015).

  44. Li, S., Li, W., Cook, C., Zhu, C. & Gao, Y. Independently recurrent neural network (indrnn): building a longer and deeper RNN. In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 5457–5466 (IEEE, 2018).

  45. Arjovsky, M., Shah, A. & Bengio, Y. Unitary evolution recurrent neural networks. In International Conference on Machine Learning 1120–1128 (ACM, 2016).

  46. Zenke, F. & Vogels, T. P. The remarkable robustness of surrogate gradient learning for instilling complex function in spiking neural networks. Neural Comput. 0, 1–27 (2021).

    MathSciNet  MATH  Google Scholar 

  47. Perez-Nieves, N., Leung, V. C., Dragotti, P. L. & Goodman, D. F. Neural heterogeneity promotes robust learning. Preprint at (2021).

  48. de Andrade, D. C., Leo, S., Viana, M. L. D. S. & Bernkopf, C. A neural attention model for speech command recognition. Preprint at (2018).

  49. Graves, A. & Schmidhuber, J. Framewise phoneme classification with bidirectional lstm and other neural network architectures. Neural Netw. 18, 602–610 (2005).

    Article  Google Scholar 

  50. Hunger, R. Floating Point Operations in Matrix-Vector Calculus (Munich Univ. Technology, 2005).

Download references


B.Y. is funded by the NWO-TTW Programme ‘Efficient Deep Learning’ (EDL) P16-25. We gratefully acknowledge the support from the organizers of the Capo Caccia Neuromorphic Cognition 2019 workshop and Neurotech CSA, as well as J. Wu and S. S. Magraner for helpful discussions.

Author information

Authors and Affiliations



B.Y., F.C. and S.B. conceived the experiments, B.Y. conducted the experiments, B.Y., F.C. and S.B. analysed the results. All authors reviewed the manuscript.

Corresponding author

Correspondence to Bojian Yin.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Peer review information Nature Machine Intelligence thanks Thomas Nowotny and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

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

Extended data

Extended Data Fig. 1 Effects of different time constant initialization schemes on network training and performance on the SoLi dataset.

a, Training accuracy b, Training Loss c, Mean Firing rate of the network. The MGconstant is the network where τ is initialized with a single value; for MGuniform the network is initialized with uniformly distributed time-constants near the single value of MGconstant; for MGstd5, a normal distribution with std 5.0 is used near the same single value.

Extended Data Fig. 2 SI-panel.

a, Bi-directional SRNN architecture. b, Computational cost computation of different layers for regular RNNs and GRU units. The computational complexity calculation follows50.

Extended Data Fig. 3 Variants of Multi-Gaussian gradient.

As illustrated, we remove either the left(MG-R) or right(MG-L) negative part of the Multi-Gaussian gradient for comparison, leaving on the ablated part the positive Gaussian gradient.

Extended Data Fig. 4 Study of different forms of gradients on ECG-LIF.

(a,b) shows the result of the using various Multi-Gaussian negative gradient ablations on the ECG-LIF task where the σ of the central (positive) Gaussian as defined in Eq (1) is varied. The effect of varying σ is shown for test accuracy (a) and sparsity (b). We find that also then, the standard Multi-Gaussian outperforms variations in terms of accuracy and sparsity.

Extended Data Fig. 5 A grid search was performed on the SoLi dataset and SHD for the h and s parameters of the multi-Gaussian surrogate gradient.

In the grid search, we calculated the performance of each pair of parameters by averaging the test accuracy and firing rate over tri-folder cross-validation. The white dashed line delineates the upper left region for models with high accuracy ( > 0.91) in (a) and high firing rate ( > 0.09) in (b). The red lines in (c) approximately delineate regions with accuracy above and below 0.87, and the white curve in (d) approximately demarcates models with an average firing rate above or below 0.1.

Supplementary information

Source data

Source Data Fig. 1

Fig. 3 Source Data.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Yin, B., Corradi, F. & Bohté, S.M. Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks. Nat Mach Intell 3, 905–913 (2021).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:

This article is cited by


Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing