# Fuentes académicas

- Goodfellow et al. (2016), cap. 10, §§10.2, 10.5, 10.7, 10.10
  https://www.deeplearningbook.org/contents/rnn.html
  Diapositivas: 1, 2, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 23, 27, 28, 34

- Hyndman y Athanasopoulos, Forecasting: Principles and Practice, cap. 5
  https://otexts.com/fpp3/toolbox.html
  Diapositivas: 2, 3, 29, 30, 31, 32, 33

- scikit-learn, Common pitfalls, §11.2: data leakage
  https://scikit-learn.org/stable/common_pitfalls.html
  Diapositivas: 3, 29

- Desarrollo y cálculo didáctico propio a partir del material UCA adjunto
  Cálculo propio, datos didácticos
  Diapositivas: 7, 8, 12, 20, 21, 22, 24, 25, 34

- Goodfellow et al. (2016), cap. 8, §§8.3–8.5
  https://www.deeplearningbook.org/contents/optimization.html
  Diapositivas: 13

- PyTorch, LSTM: ecuaciones de i, f, g, o, c y h
  https://docs.pytorch.org/docs/stable/generated/torch.nn.LSTM.html
  Diapositivas: 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 33

- Cho et al. (2014), Learning Phrase Representations, §2.3
  https://arxiv.org/abs/1406.1078
  Diapositivas: 26

- Vaswani et al. (2017), Attention Is All You Need, §3 y tabla 1
  https://arxiv.org/abs/1706.03762
  Diapositivas: 27, 28

- scikit-learn, Model evaluation: clasificación y regresión, §3.4
  https://scikit-learn.org/stable/modules/model_evaluation.html
  Diapositivas: 32