LSTM
Recurrent network with gating that lets it retain information over longer sequences.
Overview
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.
Technology Graph
How LSTM connects to the rest of the stack.
Evolution
- RNN architecture Algorithms LSTM extends RNN High ✓ source
Alternatives
-
Transformer
architecture
An alternative to LSTM · source
Comparisons
Side-by-side breakdowns with the alternatives above.