Further reading

• Learning Long-Term Dependencies with Gradient Descent is Difficult: A paper (1994) describing the difficulties of RNN to learn long-term dependencies in practice (ai.dinfo.unifi.it/paolo//ps/tnn-94-gradient.pdf)
• Long Short-Term Memory: An original paper (1997) on LSTM (www.bioinf.jku.at/publications/older/2604.pdf)
• Understanding LSTM Networks: An excellent article explaining in detail LSTM memory cells, which contains more information than this chapter (colah.github.io/posts/2015-08-Understanding-LSTMs/)
• Illustrated Guide to LSTM's and GRU's: A step by step explanation: an excellent in-depth article about LSTM and GRU (towardsdatascience.com/illustrated-guide-to-lstms-and-gru-s-a-step-by-step-explanation-44e9eb85bf21)
• Understanding LSTM and its diagrams: Another excellent article on LSTMs (medium.com/mlreview/understanding-lstm-and-its-diagrams-37e2f46f1714...