Learning in ultrametric committee machines

    Research output: Contribution to journalArticlepeer-review


    The problem of learning by examples in ultrametric committee machines (UCMs) is studied within the framework of statistical mechanics. Using the replica formalism we calculate the average generalization error in UCMs with L hidden layers and for a large enough number of units. In most of the regimes studied we find that the generalization error, as a function of the number of examples presented, develops a discontinuous drop at a critical value of the load parameter. We also find that when L>1 a number of teacher networks with the same number of hidden layers and different overlaps induce learning processes with the same critical points.
    Original languageEnglish
    Pages (from-to)887-897
    Number of pages11
    JournalJournal of Statistical Physics
    Issue number5
    Early online date21 Nov 2012
    Publication statusPublished - Nov 2012

    Bibliographical note

    The original publication is available at www.springerlink.com


    • multilayered networks
    • learning by examples


    Dive into the research topics of 'Learning in ultrametric committee machines'. Together they form a unique fingerprint.

    Cite this