the open
    research
    Contribute
    Back to the reading lists

    Deep learning· 2015

    Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

    Kaiming He (first author) · 2015

    Read the original

    DOI 10.1109/iccv.2015.123arXiv 1502.01852OpenAlex W1677182931

    On the reading lists

    Why it matters

    Introduced He initialization and PReLU, enabling reliable training of very deep rectifier networks.

    Condensed from the expert lists' notes.

    The record

    First released
    2015 (from arXiv 1502.01852)
    Citations
    21,102 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Awards
    ICCV Helmholtz Prize
    Named by
    both expert lists
    Score
    0.755 · computed rank 26 · consensus 0.68, must-read 0.5, citations percentile 0.86 (2010s · deep-learning), awards 1, 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). Each count names its source. See the method.