the open
    research
    Contribute
    Back to the reading lists

    Deep learning· 2013

    On the importance of initialization and momentum in deep learning

    Ilya Sutskever (first author) · 2013

    Read the original

    OpenAlex W104184427

    On the reading lists

    Why it matters

    Demonstrated carefully initialized networks trained with momentum could rival sophisticated second-order methods.

    Condensed from the expert lists' notes.

    The record

    First released
    2013 (from OpenAlex)
    Citations
    5,434 citations, as counted by Semantic Scholar logoSemantic Scholar (non-commercial licence)
    Named by
    both expert lists
    Score
    0.374 · computed rank 414 · consensus 0.43, must-read 0, citations percentile 0.558 (2010s · deep-learning), awards 0, existing lists 0.5. 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), and Semantic Scholar logoSemantic Scholar (used under its non-commercial API licence). Each count names its source. See the method.