IDEAS home Printed from https://ideas.repec.org/a/plo/pone00/0010955.html
   My bibliography  Save this article

Flexible Kernel Memory

Author

Listed:
  • Dimitri Nowicki
  • Hava Siegelmann

Abstract

This paper introduces a new model of associative memory, capable of both binary and continuous-valued inputs. Based on kernel theory, the memory model is on one hand a generalization of Radial Basis Function networks and, on the other, is in feature space, analogous to a Hopfield network. Attractors can be added, deleted, and updated on-line simply, without harming existing memories, and the number of attractors is independent of input dimension. Input vectors do not have to adhere to a fixed or bounded dimensionality; they can increase and decrease it without relearning previous memories. A memory consolidation process enables the network to generalize concepts and form clusters of input data, which outperforms many unsupervised clustering techniques; this process is demonstrated on handwritten digits from MNIST. Another process, reminiscent of memory reconsolidation is introduced, in which existing memories are refreshed and tuned with new inputs; this process is demonstrated on series of morphed faces.

Suggested Citation

  • Dimitri Nowicki & Hava Siegelmann, 2010. "Flexible Kernel Memory," PLOS ONE, Public Library of Science, vol. 5(6), pages 1-18, June.
    • Handle: RePEc:plo:pone00:0010955
    DOI: 10.1371/journal.pone.0010955
    as

    Download full text from publisher

    File URL: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0010955
    Download Restriction: no
    File URL: https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0010955&type=printable
    Download Restriction: no
    File URL: https://libkey.io/10.1371/journal.pone.0010955?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. Karim Nader & Glenn E. Schafe & Joseph E. Le Doux, 2000. "Fear memories require protein synthesis in the amygdala for reconsolidation after retrieval," Nature, Nature, vol. 406(6797), pages 722-726, August.
    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. Laura Arnemann & Kai A Konrad & Niklas Potrafke, 2021. "Collective memories on the 2010 European debt crisis," European Union Politics, , vol. 22(4), pages 762-784, December.
    2. Megan E. Speer & Sandra Ibrahim & Daniela Schiller & Mauricio R. Delgado, 2021. "Finding positive meaning in memories of negative events adaptively updates memory," Nature Communications, Nature, vol. 12(1), pages 1-11, December.
    3. Cecilia Forcato & Rodrigo S Fernandez & María E Pedreira, 2013. "The Role and Dynamic of Strengthening in the Reconsolidation Process in a Human Declarative Memory: What Decides the Fate of Recent and Older Memories?," PLOS ONE, Public Library of Science, vol. 8(4), pages 1-12, April.
    4. Yoav Kessler & Susan Vandermorris & Nigel Gopie & Alexander Daros & Gordon Winocur & Morris Moscovitch, 2014. "Divided Attention Improves Delayed, but Not Immediate Retrieval of a Consolidated Memory," PLOS ONE, Public Library of Science, vol. 9(3), pages 1-6, March.
    5. Cecilia Forcato & Luz Bavassi & Gabriela De Pino & Rodrigo Sebastián Fernández & Mirta Fabiana Villarreal & María Eugenia Pedreira, 2016. "Differential Left Hippocampal Activation during Retrieval with Different Types of Reminders: An fMRI Study of the Reconsolidation Process," PLOS ONE, Public Library of Science, vol. 11(3), pages 1-14, March.
    6. Cecilia Forcato & María L C Rodríguez & María E Pedreira, 2011. "Repeated Labilization-Reconsolidation Processes Strengthen Declarative Memory in Humans," PLOS ONE, Public Library of Science, vol. 6(8), pages 1-14, August.
    7. Ella Gabitov & Arnaud Boutin & Basile Pinsard & Nitzan Censor & Stuart M Fogel & Geneviève Albouy & Bradley R King & Julie Carrier & Leonardo G Cohen & Avi Karni & Julien Doyon, 2019. "Susceptibility of consolidated procedural memory to interference is independent of its active task-based retrieval," PLOS ONE, Public Library of Science, vol. 14(1), pages 1-19, January.

    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:pone00:0010955. 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.