Consistency of pseudolikelihood estimation of fully visible Boltzmann machines

    Forskningsoutput: TidskriftsbidragArtikelVetenskapligPeer review

    Sammanfattning

    A Boltzmann machine is a classic model of neural computation, and a number of methods have been proposed for its estimation. Most methods are plagued by either very slow convergence or asymptotic bias in the resulting estimates. Here we consider estimation in the basic case of fully visible Boltzmann machines. We show that the old principle of pseudo-likelihood estimation provides an estimator that is computationally very simple yet statistically consistent.
    Originalspråkengelska
    TidskriftNeural Computation
    Utgåva18
    Sidor (från-till)2283-2292
    Antal sidor10
    ISSN0899-7667
    StatusPublicerad - 2006
    MoE-publikationstypA1 Tidskriftsartikel-refererad

    Vetenskapsgrenar

    • 113 Data- och informationsvetenskap

    Citera det här