AI glossary · Machine learning
Recurrent neural network (RNN)
A recurrent neural network (RNN) is a type of neural network that reads data in sequence, one step at a time, keeping a memory of what came before.
Also called LSTM, long short-term memory, GRU, sequence-to-sequence model
In more detail
RNNs suited text, speech and time series because order matters in them. Improved versions like LSTM (long short-term memory) and GRU (gated recurrent unit) were better at remembering over longer stretches.
For language, RNNs have largely been replaced by transformers, which read whole passages at once and train much faster.
Related terms
TransformerA transformer is the neural network design behind almost every modern language model. It reads a whole passage at once and works out how its words relate.Neural networkA neural network is an AI model made of layers of connected units, loosely inspired by the brain, that learns by adjusting the strength of its connections.Attention mechanismAn attention mechanism lets an AI model focus on the most relevant parts of its input, such as which earlier words matter for understanding the current one.
Browse related tools
AI tools listed on BroUseAI in these categories.
