LSTM Model

Reference sources

Reference material used for orientation; read primary and academic sources first when claims conflict.

1. [S1] Reference

   Hochreiter and Schmidhuber (1997) -- Long short-term memory. Introduced the gated cell architecture solving the vanishing gradient problem.

   Reference

2. [S2] Reference

   Gers, Schmidhuber, and Cummins (2000) -- Learning to forget: continual prediction with LSTM. Added the forget gate, which was not in the original 1997 architecture.

   Reference

3. [S3] Reference

   Graves (2013) -- Generating sequences with recurrent neural networks. Extended LSTMs with deep stacking and demonstrated sequence generation capabilities.

   Reference

4. [S4] Reference

   Sutskever, Vinyals, and Le (2014) -- Sequence to sequence learning with neural networks. Established the encoder-decoder LSTM architecture for sequence-to-sequence tasks.

   Reference

5. [S5] Reference

   Gal and Ghahramani (2016) -- A theoretically grounded application of dropout in recurrent neural networks. Introduced variational dropout for LSTMs with the same mask at each time step.

   Reference

6. [S6] Reference

   Salinas, Flunkert, Gasthaus, and Januschowski (2020) -- DeepAR: probabilistic forecasting with autoregressive recurrent networks. LSTM-based probabilistic time-series forecasting at scale.

   Reference

7. [S7] Reference

   Makridakis, Spiliotis, and Assimakopoulos (2018) -- Statistical and machine learning forecasting methods: concerns and ways forward. M4 competition results showing LSTM performance relative to statistical methods.

   Reference