IDEAS home Printed from https://ideas.repec.org/a/plo/pcbi00/1005861.html
   My bibliography  Save this article

Stabilizing patterns in time: Neural network approach

Author

Listed:
  • Nadav Ben-Shushan
  • Misha Tsodyks

Abstract

Recurrent and feedback networks are capable of holding dynamic memories. Nonetheless, training a network for that task is challenging. In order to do so, one should face non-linear propagation of errors in the system. Small deviations from the desired dynamics due to error or inherent noise might have a dramatic effect in the future. A method to cope with these difficulties is thus needed. In this work we focus on recurrent networks with linear activation functions and binary output unit. We characterize its ability to reproduce a temporal sequence of actions over its output unit. We suggest casting the temporal learning problem to a perceptron problem. In the discrete case a finite margin appears, providing the network, to some extent, robustness to noise, for which it performs perfectly (i.e. producing a desired sequence for an arbitrary number of cycles flawlessly). In the continuous case the margin approaches zero when the output unit changes its state, hence the network is only able to reproduce the sequence with slight jitters. Numerical simulation suggest that in the discrete time case, the longest sequence that can be learned scales, at best, as square root of the network size. A dramatic effect occurs when learning several short sequences in parallel, that is, their total length substantially exceeds the length of the longest single sequence the network can learn. This model easily generalizes to an arbitrary number of output units, which boost its performance. This effect is demonstrated by considering two practical examples for sequence learning. This work suggests a way to overcome stability problems for training recurrent networks and further quantifies the performance of a network under the specific learning scheme.Author summary: The ability to learn and execute actions in fine temporal resolution is crucial, as many of our day to day actions require such temporal ordering (e.g. limb movement and speech). Indeed, generating stable time-varying outputs, using neural networks has attracted a lot of attention over the last years. One of the core problems, when facing such a task, is the solution stability, hence it was only possible to produce the sequence for a limited number of cycles. Here we propose a robust approach for the task of learning time-varying sequences.

Suggested Citation

  • Nadav Ben-Shushan & Misha Tsodyks, 2017. "Stabilizing patterns in time: Neural network approach," PLOS Computational Biology, Public Library of Science, vol. 13(12), pages 1-16, December.
  • Handle: RePEc:plo:pcbi00:1005861
    DOI: 10.1371/journal.pcbi.1005861
    as

    Download full text from publisher

    File URL: https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1005861
    Download Restriction: no

    File URL: https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1005861&type=printable
    Download Restriction: no

    File URL: https://libkey.io/10.1371/journal.pcbi.1005861?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. Claudia Clopath & Jean-Pierre Nadal & Nicolas Brunel, 2012. "Storage of Correlated Patterns in Standard and Bistable Purkinje Cell Models," PLOS Computational Biology, Public Library of Science, vol. 8(4), pages 1-10, April.
    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. Claudia Clopath & Nicolas Brunel, 2013. "Optimal Properties of Analog Perceptrons with Excitatory Weights," PLOS Computational Biology, Public Library of Science, vol. 9(2), pages 1-6, February.
    2. João Sacramento & Andreas Wichert & Mark C W van Rossum, 2015. "Energy Efficient Sparse Connectivity from Imbalanced Synaptic Plasticity Rules," PLOS Computational Biology, Public Library of Science, vol. 11(6), pages 1-24, June.
    3. Anatoly Buchin & Sarah Rieubland & Michael Häusser & Boris S Gutkin & Arnd Roth, 2016. "Inverse Stochastic Resonance in Cerebellar Purkinje Cells," PLOS Computational Biology, Public Library of Science, vol. 12(8), pages 1-31, August.
    4. Alireza Alemi & Carlo Baldassi & Nicolas Brunel & Riccardo Zecchina, 2015. "A Three-Threshold Learning Rule Approaches the Maximal Capacity of Recurrent Neural Networks," PLOS Computational Biology, Public Library of Science, vol. 11(8), pages 1-23, 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:pcbi00:1005861. 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: ploscompbiol (email available below). General contact details of provider: https://journals.plos.org/ploscompbiol/ .

    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.