the open
    research
    Contribute
    Back to the reading lists

    Deep learning· 2015

    Learning both Weights and Connections for Efficient Neural Networks

    Song Han (first author) · 2015

    Read the original

    arXiv 1506.02626OpenAlex W1845051632

    On the reading lists

    Why it matters

    Demonstrated effective train-prune-retrain pipelines achieving substantial compression without accuracy loss.

    Condensed from the expert lists' notes.

    The record

    First released
    2015 (from arXiv 1506.02626)
    Citations
    8,121 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Score
    0.364 · computed rank 441 · consensus 0.4, must-read 0, citations percentile 0.698 (2010s · deep-learning), 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.