IDEAS home Printed from https://ideas.repec.org/a/plo/pone00/0187736.html
   My bibliography  Save this article

Diffusion-based neuromodulation can eliminate catastrophic forgetting in simple neural networks

Author

Listed:
  • Roby Velez
  • Jeff Clune

Abstract

A long-term goal of AI is to produce agents that can learn a diversity of skills throughout their lifetimes and continuously improve those skills via experience. A longstanding obstacle towards that goal is catastrophic forgetting, which is when learning new information erases previously learned information. Catastrophic forgetting occurs in artificial neural networks (ANNs), which have fueled most recent advances in AI. A recent paper proposed that catastrophic forgetting in ANNs can be reduced by promoting modularity, which can limit forgetting by isolating task information to specific clusters of nodes and connections (functional modules). While the prior work did show that modular ANNs suffered less from catastrophic forgetting, it was not able to produce ANNs that possessed task-specific functional modules, thereby leaving the main theory regarding modularity and forgetting untested. We introduce diffusion-based neuromodulation, which simulates the release of diffusing, neuromodulatory chemicals within an ANN that can modulate (i.e. up or down regulate) learning in a spatial region. On the simple diagnostic problem from the prior work, diffusion-based neuromodulation 1) induces task-specific learning in groups of nodes and connections (task-specific localized learning), which 2) produces functional modules for each subtask, and 3) yields higher performance by eliminating catastrophic forgetting. Overall, our results suggest that diffusion-based neuromodulation promotes task-specific localized learning and functional modularity, which can help solve the challenging, but important problem of catastrophic forgetting.

Suggested Citation

  • Roby Velez & Jeff Clune, 2017. "Diffusion-based neuromodulation can eliminate catastrophic forgetting in simple neural networks," PLOS ONE, Public Library of Science, vol. 12(11), pages 1-24, November.
  • Handle: RePEc:plo:pone00:0187736
    DOI: 10.1371/journal.pone.0187736
    as

    Download full text from publisher

    File URL: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0187736
    Download Restriction: no

    File URL: https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0187736&type=printable
    Download Restriction: no

    File URL: https://libkey.io/10.1371/journal.pone.0187736?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. Sean B. Carroll, 2001. "Chance and necessity: the evolution of morphological complexity and diversity," Nature, Nature, vol. 409(6823), pages 1102-1109, February.
    2. Florian Engert & Tobias Bonhoeffer, 1997. "Synapse specificity of long-term potentiation breaks down at short distances," Nature, Nature, vol. 388(6639), pages 279-284, July.
    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. Fabien Lafuma & Ian J. Corfe & Julien Clavel & Nicolas Di-Poï, 2021. "Multiple evolutionary origins and losses of tooth complexity in squamates," Nature Communications, Nature, vol. 12(1), pages 1-13, December.
    2. Fan Xu & Zeng Zhou & Sergio Fagherazzi & Andrea D’Alpaos & Ian Townend & Kun Zhao & Weiming Xie & Leicheng Guo & Xianye Wang & Zhong Peng & Zhicheng Yang & Chunpeng Chen & Guangcheng Cheng & Yuan Xu &, 2024. "Anomalous scaling of branching tidal networks in global coastal wetlands and mudflats," Nature Communications, Nature, vol. 15(1), pages 1-11, December.
    3. Lashin, Sergey A. & Matushkin, Yury G. & Suslov, Valentin V. & Kolchanov, Nikolay A., 2012. "Computer modeling of genome complexity variation trends in prokaryotic communities under varying habitat conditions," Ecological Modelling, Elsevier, vol. 224(1), pages 124-129.
    4. Rajaram, R. & Castellani, B., 2016. "An entropy based measure for comparing distributions of complexity," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 453(C), pages 35-43.
    5. Xiaotong Li & Jason Karpac, 2023. "A distinct Acyl-CoA binding protein (ACBP6) shapes tissue plasticity during nutrient adaptation in Drosophila," Nature Communications, Nature, vol. 14(1), pages 1-17, December.
    6. Voorhoeve, Niels & Allan, Douglas C. & Moret, M.A. & Zebende, G.F. & Phillips, J.C., 2018. "Why human milk is more nutritious than cow milk," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 497(C), pages 302-309.
    7. Nikhil J Joshi & Giulio Tononi & Christof Koch, 2013. "The Minimal Complexity of Adapting Agents Increases with Fitness," PLOS Computational Biology, Public Library of Science, vol. 9(7), pages 1-10, July.
    8. Sotir Sotirov & Evdokia Sotirova & Vassia Atanassova & Krassimir Atanassov & Oscar Castillo & Patricia Melin & Todor Petkov & Stanimir Surchev, 2018. "A Hybrid Approach for Modular Neural Network Design Using Intercriteria Analysis and Intuitionistic Fuzzy Logic," Complexity, Hindawi, vol. 2018, pages 1-11, April.
    9. Cazzolla Gatti, Roberto, 2021. "A multi-armed bandit algorithm speeds up the evolution of cooperation," Ecological Modelling, Elsevier, vol. 439(C).
    10. Tamar Friedlander & Avraham E Mayo & Tsvi Tlusty & Uri Alon, 2013. "Mutation Rules and the Evolution of Sparseness and Modularity in Biological Systems," PLOS ONE, Public Library of Science, vol. 8(8), pages 1-10, 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:plo:pone00:0187736. 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: plosone (email available below). General contact details of provider: https://journals.plos.org/plosone/ .

    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.