RNN
Recurrent neural network that carries a hidden state along a sequence.
Aperçu
A recurrent neural network processes a sequence one step at a time, carrying a hidden state that summarises what it has seen. It solves the problem that a fixed-size input cannot represent a sequence of arbitrary length. It exists because order matters in language and time series. Training it is slow and unstable over long sequences, which is the limitation the Transformer was designed to remove.
Graphe des technologies
Comment RNN se rattache au reste de la pile.
Utilise et dépend de
- Neural Network concept Algorithms RNN based on Neural Network High ✓ source
Evolution
- LSTM architecture Algorithms LSTM extends RNN High ✓ source
Alternatives
-
Transformer
architecture
Une alternative à RNN · source
Comparaisons
Comparaisons détaillées avec les alternatives ci-dessus.