the open
    research
    Contribute
    Back to the reading lists

    Machine learning foundations· 2015

    Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

    Yarin Gal (first author) · 2015 · published 2016

    Read the original

    arXiv 1506.02142OpenAlex W582134693

    On the reading lists

    Why it matters

    Reinterpreted dropout as approximate Bayesian inference, enabling inexpensive predictive uncertainty estimates.

    Condensed from the expert lists' notes.

    The record

    First released
    2015 (from arXiv 1506.02142)
    Published
    2016
    Citations
    13,239 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Score
    0.449 · computed rank 294 · consensus 0.33, must-read 0, citations percentile 1 (2010s · foundations), awards 0, existing lists 0. Method

    Data sources

    Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.