Architectures · intermediate · concept 84 of 311 · Updated Nov 4, 2026
LSTM (Long Short-Term Memory)
An RNN variant that solves the vanishing gradient problem using gates (forget, input, output) that control information flow. Was the dominant sequence architecture before Transformers.
Top AI contributors on this
- Geoffrey HintonUniversity of Toronto (emeritus)
- Yoshua BengioLawZero / Université de Montréal
- Yann LeCunAMI Labs / NYU
- Andrew NgDeepLearning.AI / AI Fund
- Ilya SutskeverSafe Superintelligence Inc. (SSI)
- Andrej KarpathyAnthropic
Key terms
Forget gateInput gateOutput gateCell stateGRU
Learn these first
Videos
▶ Long Short-Term Memory (LSTM), Clearly Explained ↗
StatQuest with Josh Starmer · YouTube
▶ Recurrent Neural Networks (RNNs), Clearly Explained!!! ↗
StatQuest with Josh Starmer · YouTube
Guides and articles
This unlocks