GRU
A streamlined LSTM — a recurrent network that remembers across sequences with fewer moving parts, trading a little capacity for speed and simplicity.
Reviewed July 15, 2026Stable
When not to use it
- For most large-scale sequence tasks in 2026 — a transformer usually outperforms it if you have the data and compute.
- When you specifically need maximum memory capacity — an LSTM occasionally edges it out.
- For very long-range dependencies where attention or state-space models handle the range better.
Reach for something else instead
- LSTM — the more elaborate sibling, occasionally higher-capacity.
- Transformer — the modern default for most sequence tasks, at higher compute cost.
- State-space models (Mamba) — the efficient-recurrence revival for long sequences.
Further reading
- Cho et al. (2014), Learning Phrase Representations using RNN Encoder-Decoder — introduced the GRU.
- Chung et al. (2014), Empirical Evaluation of Gated Recurrent Neural Networks — the GRU-vs-LSTM comparison.
- Goodfellow, Bengio & Courville, Deep Learning — gated recurrent architectures.
Primary sources, listed so you can check the claims on this page rather than take them on trust.
Where people go wrong
- Agonising over GRU vs. LSTM when they usually perform within noise of each other — just try both.
- Reaching for recurrence at all when a transformer would clearly win and resources allow.
- Forgetting that the update gate's carry-forward is what prevents vanishing gradients — the whole point of gating.
At a glance
FieldDeep Learning
What it isa simplified LSTM
Gatesupdate + reset (vs. LSTM's three)
Tradea little capacity for speed
DifficultyIntermediate
Where this sits
A destination. 12 concepts lead here, and nothing in the corpus depends on it.
9Levelsteps in
12Needs firstconcepts
0Opens upnothing further
1Areastays here
Learn these firstLSTM
Computed from the prerequisite graph, not assigned. How this works