Historical milestone · 1997

    Long Short-Term Memory

    Reviewed through September 18, 2026

    1997 · Historical milestone

    Long Short-Term Memory

    Era
    1990s
    Theme
    Language models & representation
    Evidence form
    Introduced gated memory cells and constant-error flow to address vanishing gradients on long temporal dependencies
    School / paradigm
    Recurrent neural networks
    Institution / context
    TU Munich / IDSIA
    Researchers
    Sepp Hochreiter; Jürgen Schmidhuber

    School of thought

    Connectionism

    Matched on representative researcher.

    Cognition emerges from learned distributed representations and weighted interactions among simple units.

    Critique. Opacity, data/compute demands, unstable optimization, and weak guarantees or causal grounding.

    Modern descendants. Foundation models, multimodal networks, representation learning, and differentiable agents.

    Understand

    Plain-language record, transferred from the reviewed source module.

    Theory or experimental setup. Enabled recurrent networks to preserve and learn information across much longer sequences.

    Result / historical claim. Sequential computation limits parallelism; memory remains finite and training can still be difficult.

    Apply

    Professional implication, only where the reviewed record states one.

    The checked-in record does not state a separate professional application for this entry. The topic page places it in the wider research lineage: .

    Verify

    Evidence status, stated limitations, and the external sources this record actually carries.

    Evidence form. Introduced gated memory cells and constant-error flow to address vanishing gradients on long temporal dependencies

    Limitation / debate. Sequence modeling, gated state, long-context memory, and recurrent components in agents.

    Source status. This milestone row does not carry a primary-source URL in the approved export, and we do not have a verified link for it in our own research. We do not guess one.

    No primary-source URL is recorded for this entry in our reviewed data. Rather than manufacture a citation, we link the Implement Agentic research page that carries the record.

    Reproduce

    A reproduction tutorial is linked only when one exists for this exact record.

    A reproduction tutorial is not yet available for this entry. The closest reviewed material is .

    Cite or share

    APA-like: This historical record carries a year only, and no author or publisher of record in the checked-in data. An APA reference would have to invent that metadata.

    BibTeX: BibTeX requires an author and publication venue. Historical lineage entries store a narrative record and its source link, not structured authorship, so the field would be fabricated.

    Related

    Appears in Reasoning enters real-time multimodal interaction.