LSTM

Überblick

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.

Technologiegraph

Wie LSTM mit dem übrigen Stack zusammenhängt.

Alternativen

• Transformer architecture

  Eine Alternative zu LSTM · source

Vergleiche

Detaillierte Gegenüberstellungen mit den Alternativen oben.

• Transformer vs LSTM