IDEAS home Printed from https://ideas.repec.org/a/nat/natcom/v11y2020i1d10.1038_s41467-020-17236-y.html
   My bibliography  Save this article

A solution to the learning dilemma for recurrent networks of spiking neurons

Author

Listed:
  • Guillaume Bellec

    (Graz University of Technology)

  • Franz Scherr

    (Graz University of Technology)

  • Anand Subramoney

    (Graz University of Technology)

  • Elias Hajek

    (Graz University of Technology)

  • Darjan Salaj

    (Graz University of Technology)

  • Robert Legenstein

    (Graz University of Technology)

  • Wolfgang Maass

    (Graz University of Technology)

Abstract

Recurrently connected networks of spiking neurons underlie the astounding information processing capabilities of the brain. Yet in spite of extensive research, how they can learn through synaptic plasticity to carry out complex network computations remains unclear. We argue that two pieces of this puzzle were provided by experimental data from neuroscience. A mathematical result tells us how these pieces need to be combined to enable biologically plausible online network learning through gradient descent, in particular deep reinforcement learning. This learning method–called e-prop–approaches the performance of backpropagation through time (BPTT), the best-known method for training recurrent neural networks in machine learning. In addition, it suggests a method for powerful on-chip learning in energy-efficient spike-based hardware for artificial intelligence.

Suggested Citation

  • Guillaume Bellec & Franz Scherr & Anand Subramoney & Elias Hajek & Darjan Salaj & Robert Legenstein & Wolfgang Maass, 2020. "A solution to the learning dilemma for recurrent networks of spiking neurons," Nature Communications, Nature, vol. 11(1), pages 1-15, December.
    • Handle: RePEc:nat:natcom:v:11:y:2020:i:1:d:10.1038_s41467-020-17236-y
    DOI: 10.1038/s41467-020-17236-y
    as

    Download full text from publisher

    File URL: https://www.nature.com/articles/s41467-020-17236-y
    File Function: Abstract
    Download Restriction: no
    File URL: https://libkey.io/10.1038/s41467-020-17236-y?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Melika Payvand & Filippo Moro & Kumiko Nomura & Thomas Dalgaty & Elisa Vianello & Yoshifumi Nishi & Giacomo Indiveri, 2022. "Self-organization of an inhomogeneous memristive hardware for sequence learning," Nature Communications, Nature, vol. 13(1), pages 1-12, December.
    2. Barbara Feulner & Matthew G. Perich & Raeed H. Chowdhury & Lee E. Miller & Juan A. Gallego & Claudia Clopath, 2022. "Small, correlated changes in synaptic connectivity may facilitate rapid motor learning," Nature Communications, Nature, vol. 13(1), pages 1-14, December.
    3. Hanle Zheng & Zhong Zheng & Rui Hu & Bo Xiao & Yujie Wu & Fangwen Yu & Xue Liu & Guoqi Li & Lei Deng, 2024. "Temporal dendritic heterogeneity incorporated with spiking neural networks for learning multi-timescale dynamics," Nature Communications, Nature, vol. 15(1), pages 1-20, December.
    4. Michalis Pagkalos & Spyridon Chavlis & Panayiota Poirazi, 2023. "Introducing the Dendrify framework for incorporating dendrites to spiking neural networks," Nature Communications, Nature, vol. 14(1), pages 1-16, December.
    5. Zhiwei Chen & Wenjie Li & Zhen Fan & Shuai Dong & Yihong Chen & Minghui Qin & Min Zeng & Xubing Lu & Guofu Zhou & Xingsen Gao & Jun-Ming Liu, 2023. "All-ferroelectric implementation of reservoir computing," Nature Communications, Nature, vol. 14(1), pages 1-12, December.
    6. Rohit Abraham John & Yiğit Demirağ & Yevhen Shynkarenko & Yuliia Berezovska & Natacha Ohannessian & Melika Payvand & Peng Zeng & Maryna I. Bodnarchuk & Frank Krumeich & Gökhan Kara & Ivan Shorubalko &, 2022. "Reconfigurable halide perovskite nanocrystal memristors for neuromorphic computing," Nature Communications, Nature, vol. 13(1), pages 1-10, December.
    7. Matteo Saponati & Martin Vinck, 2023. "Sequence anticipation and spike-timing-dependent plasticity emerge from a predictive learning rule," Nature Communications, Nature, vol. 14(1), pages 1-13, December.
    8. Francesco Barchi & Luca Zanatta & Emanuele Parisi & Alessio Burrello & Davide Brunelli & Andrea Bartolini & Andrea Acquaviva, 2021. "Spiking Neural Network-Based Near-Sensor Computing for Damage Detection in Structural Health Monitoring," Future Internet, MDPI, vol. 13(8), pages 1-22, August.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:nat:natcom:v:11:y:2020:i:1:d:10.1038_s41467-020-17236-y. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.nature.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.