Methods › Sequential › Recurrent Neural Networks › LSTM

Long Short-Term Memory

LSTM

introduced 1997 5,448 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla RNNs through additional cells, input and output gates. Intuitively, vanishing gradients are solved through additional additive components, and forget gate activations, that allow the gradients to flow through the network without vanishing as quickly.

(Image Source here)

(Introduced by Hochreiter and Schmidhuber)

Papers archive 2025-07-28

30 shown of 5,448, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 1,283 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Sentence427
Time Series398
Language Modelling390
Time Series Analysis334
Decoder330
Language Modeling318
General Classification301
Neural Architecture Search273
Prediction258
Sentiment Analysis258
Machine Translation226
Word Embeddings209
Translation204
Classification200
Deep Learning200
Speech Recognition193
speech-recognition183
Transfer Learning159
Reinforcement Learning151
Text Classification139

Usage over time archive 2025-07-28

Papers per year tagged with LSTM: 2014 to 2025, peak 923 923 0 2014: 13 papers 2014 2015: 56 papers 2015 2016: 175 papers 2016 2017: 316 papers 2017 2018: 612 papers 2018 2019: 923 papers 2019 2020: 876 papers 2020 2021: 750 papers 2021 2022: 499 papers 2022 2023: 502 papers 2023 2024: 491 papers 2024 2025: 235 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (5,448 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Recurrent Neural Networks

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections