Advanced Forecasting with Python: With State-of-the-Art-Models Including LSTMs, Facebook’s Prophet, and Amazon’s DeepAR

© 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_17

17. RNNs Using SimpleRNN and GRU

Joos Korstanje¹  

(1)

Maisons Alfort, France

 

In this chapter, you’ll discover a more advanced version of neural networks called Recurrent Neural Networks . There are three very common versions of RNNs: SimpleRNN, GRU (Gated Recurrent Unit), and LSTM (Long Short Term Memory). In practice, SimpleRNNs are hardly used anymore for a number of problems that I’ll talk about later. Therefore, I have regrouped SimpleRNN and GRU in this chapter, and LSTMs have their own chapter.

What Are RNNs: Architecture

So what are Recurrent Neural Networks, and ...