IDEAS home Printed from https://ideas.repec.org/a/nat/natcom/v14y2023i1d10.1038_s41467-023-37562-1.html
   My bibliography  Save this article

Meta-learning biologically plausible plasticity rules with random feedback pathways

Author

Listed:
  • Navid Shervani-Tabar

    (University of Notre Dame)

  • Robert Rosenbaum

    (University of Notre Dame)

Abstract

Backpropagation is widely used to train artificial neural networks, but its relationship to synaptic plasticity in the brain is unknown. Some biological models of backpropagation rely on feedback projections that are symmetric with feedforward connections, but experiments do not corroborate the existence of such symmetric backward connectivity. Random feedback alignment offers an alternative model in which errors are propagated backward through fixed, random backward connections. This approach successfully trains shallow models, but learns slowly and does not perform well with deeper models or online learning. In this study, we develop a meta-learning approach to discover interpretable, biologically plausible plasticity rules that improve online learning performance with fixed random feedback connections. The resulting plasticity rules show improved online training of deep models in the low data regime. Our results highlight the potential of meta-learning to discover effective, interpretable learning rules satisfying biological constraints.

Suggested Citation

  • Navid Shervani-Tabar & Robert Rosenbaum, 2023. "Meta-learning biologically plausible plasticity rules with random feedback pathways," Nature Communications, Nature, vol. 14(1), pages 1-12, December.
    • Handle: RePEc:nat:natcom:v:14:y:2023:i:1:d:10.1038_s41467-023-37562-1
    DOI: 10.1038/s41467-023-37562-1
    as

    Download full text from publisher

    File URL: https://www.nature.com/articles/s41467-023-37562-1
    File Function: Abstract
    Download Restriction: no
    File URL: https://libkey.io/10.1038/s41467-023-37562-1?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
    ---><---

    References listed on IDEAS

    as
    1. Timothy P. Lillicrap & Daniel Cownden & Douglas B. Tweed & Colin J. Akerman, 2016. "Random synaptic feedback weights support error backpropagation for deep learning," Nature Communications, Nature, vol. 7(1), pages 1-10, December.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Robert Rosenbaum, 2022. "On the relationship between predictive coding and backpropagation," PLOS ONE, Public Library of Science, vol. 17(3), pages 1-27, March.
    2. Michele N. Insanally & Badr F. Albanna & Jade Toth & Brian DePasquale & Saba Shokat Fadaei & Trisha Gupta & Olivia Lombardi & Kishore Kuchibhotla & Kanaka Rajan & Robert C. Froemke, 2024. "Contributions of cortical neuron firing patterns, synaptic connectivity, and plasticity to task performance," Nature Communications, Nature, vol. 15(1), pages 1-21, December.
    3. Keitaro Obara & Teppei Ebina & Shin-Ichiro Terada & Takanori Uka & Misako Komatsu & Masafumi Takaji & Akiya Watakabe & Kenta Kobayashi & Yoshito Masamizu & Hiroaki Mizukami & Tetsuo Yamamori & Kiyoto , 2023. "Change detection in the primate auditory cortex through feedback of prediction error signals," Nature Communications, Nature, vol. 14(1), pages 1-17, December.
    4. Giorgia Dellaferrera & Stanisław Woźniak & Giacomo Indiveri & Angeliki Pantazi & Evangelos Eleftheriou, 2022. "Introducing principles of synaptic integration in the optimization of deep neural networks," Nature Communications, Nature, vol. 13(1), pages 1-14, December.
    5. Mitsumasa Nakajima & Katsuma Inoue & Kenji Tanaka & Yasuo Kuniyoshi & Toshikazu Hashimoto & Kohei Nakajima, 2022. "Physical deep learning with biologically inspired training method: gradient-free approach for physical hardware," Nature Communications, Nature, vol. 13(1), pages 1-12, December.
    6. Ertam, Fatih, 2019. "An efficient hybrid deep learning approach for internet security," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 535(C).
    7. Alexander Ororbia & Daniel Kifer, 2022. "The neural coding framework for learning generative models," Nature Communications, Nature, vol. 13(1), pages 1-14, December.
    8. Stefano Recanatesi & Gabriel Koch Ocker & Michael A Buice & Eric Shea-Brown, 2019. "Dimensionality in recurrent spiking networks: Global trends in activity and local origins in connectivity," PLOS Computational Biology, Public Library of Science, vol. 15(7), pages 1-29, July.

    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:14:y:2023:i:1:d:10.1038_s41467-023-37562-1. 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.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with 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.