the open
    research
    Contribute
    Back to the reading lists

    Deep learning· 1994

    Learning long-term dependencies with gradient descent is difficult

    Yoshua Bengio (first author) · 1994

    Read the original

    DOI 10.1109/72.279181OpenAlex W2107878631

    On the reading lists

    Why it matters

    Explained fundamental difficulties learning long-range dependencies through gradient descent in recurrent networks.

    Condensed from the expert lists' notes.

    The record

    First released
    1994 (from OpenAlex)
    Citations
    8,539 citations, as counted by OpenAlex (CC0)
    Named by
    both expert lists
    Score
    0.457 · computed rank 283 · consensus 0.58, must-read 0.5, citations percentile 0.667 (1990s · 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.