the open
    research
    Contribute
    Back to the reading lists

    Deep learning· 2006

    A Fast Learning Algorithm for Deep Belief Nets

    Geoffrey E. Hinton (first author) · 2006

    Read the original

    DOI 10.1162/neco.2006.18.7.1527OpenAlex W2136922672

    On the reading lists

    Why it matters

    Demonstrated effective greedy layerwise training, helping revive research into deep neural networks.

    Condensed from the expert lists' notes.

    The record

    First released
    2006 (from OpenAlex)
    Citations
    16,335 citations, as counted by OpenAlex (CC0)
    Named by
    both expert lists
    Also relevant to
    Generative models, Computer vision & multimodal
    Score
    0.704 · computed rank 69 · consensus 0.79, must-read 1, citations percentile 0.907 (2000s · all domains), awards 0, existing lists 0.5. Method

    Editor's notes

    • Readability check: fail: Historically important, but the greedy layer-wise method is no longer used and the paper is hard going. (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.