Historical milestone · 1990
Simple recurrent networks
Reviewed through September 18, 2026
1990 · Historical milestone
Simple recurrent networks
- Era
- 1990s
- Theme
- Language models & representation
- Evidence form
- Trained a recurrent network to predict the next element in structured sequences and analyzed its hidden-state organization
- School / paradigm
- Connectionist sequence learning
- Institution / context
- UC San Diego
- Researchers
- Jeffrey Elman
Researcher index
Jeffrey Elman
Sequence learning · UC San Diego
Simple recurrent networks
Why it still matters. Showed predictive learning can induce temporal and grammatical structure.
Representative source for this researcher — not necessarily the source of this milestone: https://doi.org/10.1207/s15516709cog1402_1 (opens in a new tab)
Understand
Plain-language record, transferred from the reviewed source module.
Theory or experimental setup. Showed that prediction can induce representations of temporal and grammatical structure without explicit symbolic rules.
Result / historical claim. Simple RNNs struggle with long dependencies and unstable gradients.
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: Language models and representation.
Verify
Evidence status, stated limitations, and the external sources this record actually carries.
Evidence form. Trained a recurrent network to predict the next element in structured sequences and analyzed its hidden-state organization
Limitation / debate. Autoregressive pretraining, recurrent state, sequence representations, and predictive learning.
Source status. The source link below is the verified link our reviewed topic research already carries for this milestone.
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 Language models and representation.
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.
