the open
    research
    Contribute
    Back to the reading lists

    Machine learning foundations· 2016

    Understanding deep learning requires rethinking generalization

    Chiyuan Zhang (first author) · 2016 · published 2017

    Read the original

    arXiv 1611.03530OpenAlex W2950220847

    On the reading lists

    Why it matters

    Showed neural networks can memorize random labels, challenging classical explanations of generalization.

    Condensed from the expert lists' notes.

    The record

    First released
    2016 (from arXiv 1611.03530)
    Published
    2017
    Citations
    5,332 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Also relevant to
    Deep learning
    Score
    0.587 · computed rank 163 · consensus 0.48, must-read 1, citations percentile 0.838 (2010s · foundations), awards 0, existing lists 0.5. Method

    Editor's notes

    • Readability check: pass: Short experiments that changed how the field thinks about generalisation. (AI draft (Claude), not yet reviewed, 2026-10-29)

    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.