seniorDeep Learning
What is a Recurrent Neural Network (RNN) and why is it used for sequential data?
Updated May 16, 2026
Short answer
RNNs are neural networks designed to process sequential data by maintaining a hidden state that captures temporal dependencies.
Deep explanation
Many real-world datasets are sequential in nature:
- Text.
- Time series.
- Speech.
RNNs model sequences by maintaining memory of previous inputs.
Core mechanism: At each timestep:
- Input + previous hidden state → new hidden state
Formula: h_t = tanh(Wx_t + Uh_{t-1})
Key idea: The hidden state acts as memory.
Advantages:
- Handles variable-length sequences.
- Captures temporal dependencies.
Limitations:
- Vanishing gradients.
- Difficulty learning long-term dependencies.
Variants:
- LSTM:
- Introduces gates to control memory flow.
- GRU:
- Simplified version of LSTM.…
Unlock with a Pro subscription to view this section.
View pricingReal-world example
No real-world example available yet.
Unlock with a Pro subscription to view this section.
Upgrade to ProCommon mistakes
No common mistakes listed yet.
Unlock with a Pro subscription to view this section.
Upgrade to ProFollow-up questions
No follow-up questions available yet.
Unlock with a Pro subscription to view this section.
Upgrade to Pro