Glossary · Deep learning
What is GRU? Definition and meaning
A recurrent unit with fewer gates than an LSTM, often similarly accurate and faster to train.
Definition
GRU: A recurrent unit with fewer gates than an LSTM, often similarly accurate and faster to train.
In short: A lighter gated recurrent network.
When it is used
Time-series and sequence modelling with tighter compute budgets.
Where it fits
GRU belongs to Architectures in the Deep learning topic. These are the other terms in the same group:
- CNN: Networks that apply learned filters across local neighbourhoods, sharing weights over positions.
- Recurrent neural networks: A neural network that processes a sequence one step at a time, updating a hidden state that summarises everything seen so far.
- LSTM: A recurrent network with gates that control what is stored, forgotten and emitted over time.
- Transformers: Neural networks built on self-attention, letting every element of the input weigh every other element.
- ResNet: A convolutional architecture whose residual connections make very deep networks trainable.
- ViT: Splits an image into patches and processes them as a sequence with a transformer.
- Autoencoders: A network that encodes an input into a smaller code and decodes it back, learning what matters.
- VAE: An autoencoder that learns a distribution over a latent space and is trained with a variational objective.
- GAN: Two networks compete: a generator produces samples and a discriminator tries to tell them from real data.
- Diffusion models: Generative models that learn to denoise data step by step, turning noise into a sample.
Learn more
The full guide to GRU explains how it works, when to use it and how it compares with the alternatives, with examples. The glossary lists every term on the site from A to Z.
Previous term: gRPC · Next term: Guardrails