the open
    research
    Contribute
    Back to the reading lists

    Deep learning· 2016

    Identity Mappings in Deep Residual Networks

    He (first author) · 2016

    Read the original

    DOI 10.1007/978-3-319-46493-0_38arXiv 1603.05027OpenAlex W2302255633

    On the reading lists

    Why it matters

    Showed pre-activation identity mappings ease very deep training.

    Condensed from the expert lists' notes.

    The record

    First released
    2016 (from arXiv 1603.05027)
    Citations
    11,461 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Score
    0.454 · computed rank 289 · consensus 0.285, must-read 0, citations percentile 0.767 (2010s · deep-learning), awards 0, existing lists 1. 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.