the open
    research
    Contribute
    Back to the reading lists

    Deep learning· 1989

    Approximation by superpositions of a sigmoidal function

    George Cybenko (first author) · 1989

    Read the original

    DOI 10.1007/bf02551274OpenAlex W2103496339

    On the reading lists

    Why it matters

    Proved single-hidden-layer sigmoidal networks can approximate arbitrary continuous functions on compact domains.

    Condensed from the expert lists' notes.

    The record

    First released
    1989 (from OpenAlex)
    Citations
    13,883 citations, as counted by OpenAlex (CC0)
    Named by
    both expert lists
    Score
    0.538 · computed rank 199 · consensus 0.76, must-read 1, citations percentile 0.6 (1980s · deep-learning), awards 0, existing lists 0. Method

    Editor's notes

    • Readability check: pass: Cybenko's universal approximation theorem; short proof. (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.