GRU vs LSTM — how are they different in practice?
mediumAnswer
- GRU merges forget + input gates into an update gate and drops the separate cell state (uses only h).
- Fewer parameters (~25% less), often trains faster, similar accuracy on most sequence tasks.
- LSTM is a bit more expressive on very long sequences with complex temporal dynamics.
- Rule of thumb: try GRU first for simplicity; use LSTM when GRU underfits.
Check yourself — multiple choice
- GRU has more parameters than LSTM
- GRU merges gates and drops cell state — fewer params, faster, similar accuracy to LSTM on most tasks
- Same architecture
- GRU has no gates
GRU: merged gates, no cell state → fewer params, similar accuracy.
#rnn#lstm#gru
Practise Deep Learning
214 interview questions in this topic.
Related questions
- Explain the four gates of an LSTM.
- Why did transformers replace RNNs for sequence modeling?
- When is orthogonal weight initialization useful?
- What causes exploding gradients and how do you handle them?
- Why is BatchNorm awkward in RNNs?
- Write the vanilla RNN update equation and explain why it struggles with long sequences.