Parallel strategy for optimal learning in perceptrons

    Research output: Contribution to journalArticlepeer-review


    We developed a parallel strategy for learning optimally specific realizable rules by perceptrons, in an online learning scenario. Our result is a generalization of the Caticha–Kinouchi (CK) algorithm developed for learning a perceptron with a synaptic vector drawn from a uniform distribution over the N-dimensional sphere, so called the typical case. Our method outperforms the CK algorithm in almost all possible situations, failing only in a denumerable set of cases. The algorithm is optimal in the sense that it saturates Bayesian bounds when it succeeds.
    Original languageEnglish
    Article number125101
    Pages (from-to)125101
    Number of pages1
    JournalJournal of Physics A: Mathematical and Theoretical
    Issue number12
    Publication statusPublished - 26 Mar 2010

    Bibliographical note

    © 2010 IOP Publishing Ltd.


    • learning
    • realizable rules
    • perceptrons
    • Caticha–Kinouchi algorithm
    • synaptic vector
    • N-dimensional sphere
    • Bayesian bounds


    Dive into the research topics of 'Parallel strategy for optimal learning in perceptrons'. Together they form a unique fingerprint.

    Cite this