Recurrent Neural Network (RNN)
A recurrent neural network is a neural network for sequences, such as text or time series, that processes one step at a time while carrying a memory of earlier steps.
What is Recurrent Neural Network (RNN)?
RNNs were the standard for speech recognition and translation before transformers. Basic RNNs struggle to remember information over long sequences, which led to improved designs such as LSTMs.
How it works
At each step the network combines the current input with its hidden state from the previous step to produce an output and an updated state.
← All Artificial Intelligence & Superintelligence definitions · ← Back to the A–Z definitions