LSTM
LSTM was proposed for sequence dependencies.
Why it matters
LSTM addressed the difficulty of retaining information over long sequences.
Its result concerns a recurrent architecture, not every later language model.
Research · November 1997
Placed by the contemporary primary publication. The exact event date is not known; its documented interval appears below.
Event record
- Event date
- 1997
- Timeline date
- Primary publication date
- Verification
- Sources gathered automatically · September 11, 2026
- Lines
- ID
- evt-0005
Sources
- primary Long Short-Term Memory
Neural Computation · Published November 1997
Related events
- Related Back-propagation
A recurrent architecture is trained by the gradient method popularised earlier.
Records that link to this one
- Builds on Sequence-to-sequence
The authors explicitly use multilayer LSTM networks to encode the input sequence and generate a translation.
Sequence to Sequence Learning - Related Finding Structure in Time
The recurrent scheme whose limitation LSTM later solves.
- Related The vanishing gradient problem
LSTM in 1997 is the direct answer to this diagnosis.
- Related Why long-term dependencies are not learned
With Hochreiter's work it justifies the need for a new recurrent scheme.
- Related Mamba
The model belongs to the line of recurrent schemes with a controlled state.
- Builds on The gated recurrent unit (GRU)
The preprint says the new hidden unit was motivated by the LSTM unit but is much simpler.
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation