Architectures · intermediate · concept 83 of 311 · Updated Nov 4, 2026
Recurrent Neural Network (RNN)
Architecture for sequential data that maintains a hidden state across time steps. Suffers from vanishing gradients for long sequences, largely replaced by Transformers but still relevant for understanding.
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
Hidden stateVanishing gradientSequence-to-sequenceTime steps
Learn these first
Videos
▶ Recurrent Neural Networks (RNNs), Clearly Explained!!! ↗
StatQuest with Josh Starmer · YouTube
▶ The Power of Recurrent Neural Networks (RNN) ↗
IBM Technology · YouTube
Guides and articles