IDEAS home Printed from https://ideas.repec.org/a/eee/phsmap/v660y2025ics0378437125000081.html
   My bibliography  Save this article

Phase transition analysis for shallow neural networks with arbitrary activation functions

Author

Listed:
  • Citton, Otavio
  • Richert, Frederieke
  • Biehl, Michael

Abstract

In this work we extend the statistical physics based analysis of so-called soft committee machines (SCM), two-layered feedforward neural networks with differentiable hidden unit activation, in student–teacher model scenarios. In particular, we study phase transitions with the training set size as observed in off-line learning for SCM with arbitrary activation functions. The analysis is facilitated by expanding the relevant quantities in a basis of Hermite polynomials and truncating the expansion to a relatively small number of terms. We derive a sufficient condition for the presence of a second order phase transition and find an analytical expression for the point in training where an unspecialized phase becomes unstable. In addition we derive an expression for the asymptotic learning behavior for general activation functions. Moreover, we demonstrate that the approach facilitates the treatment of mismatched scenarios, where student and teacher network have different activation functions. This enables the investigation of more realistic learning scenarios within the statistical physics framework.

Suggested Citation

  • Citton, Otavio & Richert, Frederieke & Biehl, Michael, 2025. "Phase transition analysis for shallow neural networks with arbitrary activation functions," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 660(C).
  • Handle: RePEc:eee:phsmap:v:660:y:2025:i:c:s0378437125000081
    DOI: 10.1016/j.physa.2025.130356
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0378437125000081
    Download Restriction: Full text for ScienceDirect subscribers only. Journal offers the option of making the article available online on Science direct for a fee of $3,000

    File URL: https://libkey.io/10.1016/j.physa.2025.130356?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
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    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:eee:phsmap:v:660:y:2025:i:c:s0378437125000081. 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: Catherine Liu (email available below). General contact details of provider: http://www.journals.elsevier.com/physica-a-statistical-mechpplications/ .

    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.