20
Recurrent Neural Networks
In this chapter, we analyze recurrent neural networks (RNNs). In order for a neural network to fully manage the temporal dimension, it is necessary to introduce advanced recurrent layers, whose performance must be greater than any other regression method (in several contexts, like forecasting and deep reinforcement learning).
In particular, in this chapter, we are going to discuss the following topics:
- Recurrent neural networks
- LSTM and GRU cells
- Transfer learning
The first topic we need to discuss is the concept of the RNN focusing on its structure, abilities and limitations. Starting with this knowledge, we can continue the exploration of more complex algorithms that can outperform standard time-series methods. ...
Get Mastering Machine Learning Algorithms - Second Edition 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.
