LSTM
Recurrent network with gating that lets it retain information over longer sequences.
Resumen
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.
Grafo de tecnologías
Cómo se conecta LSTM con el resto del stack.
Evolution
- RNN architecture Algorithms LSTM extends RNN High ✓ source
Alternativas
-
Transformer
architecture
Una alternativa a LSTM · source
Comparativas
Comparativas detalladas con las alternativas anteriores.