LSTM
Recurrent network with gating that lets it retain information over longer sequences.
Обзор
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.
Граф технологий
Как LSTM связана с остальным стеком.
Evolution
- RNN architecture Algorithms LSTM extends RNN High ✓ source
Альтернативы
-
Transformer
architecture
Альтернатива для LSTM · source
Сравнения
Подробные сопоставления с альтернативами выше.