© The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature 2021
J. KorstanjeAdvanced Forecasting with Pythonhttps://doi.org/10.1007/978-1-4842-7150-6_18

18. LSTM RNNs

Joos Korstanje1  
(1)
Maisons Alfort, France
 

In the previous chapter, you have discovered two types of Recurrent Neural Network cells called SimpleRNN and GRU (Gated Recurrent Unit). In this chapter, you’ll discover a third type of cell called LSTM, for Long Short-Term Memory .

What Is LSTM

LSTMs as a third and last type of RNN cell are even more advanced than the GRU cell. If you remember from the last chapter, the SimpleRNN cell allows having recurrent architectures, by adding a feedback loop between consecutive values. It therefore is an improvement on “simple” ...

Get Advanced Forecasting with Python: With State-of-the-Art-Models Including LSTMs, Facebook’s Prophet, and Amazon’s DeepAR now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.