LSTM
Recurrent network with gating that lets it retain information over longer sequences.
Aperçu
An LSTM is a recurrent network whose internal gates decide what to keep, what to write and what to output, which slows the decay of information across many steps. It solves the vanishing-gradient problem that made plain recurrent networks forget the beginning of a long sequence. It exists because much of the useful context in language is far from the token being predicted. It was the standard sequence model before attention replaced it.
Graphe des technologies
Comment LSTM se rattache au reste de la pile.
Evolution
- RNN architecture Algorithms LSTM extends RNN High ✓ source
Alternatives
-
Transformer
architecture
Une alternative à LSTM · source
Comparaisons
Comparaisons détaillées avec les alternatives ci-dessus.