In this chapter, we learned about Recurrent Neural Networks (RNNs). We learned about the various variants of RNN and described two of them in detail: Long Short-Term Memory (LSTM) networks and Gated Recurrent Unit (GRU) networks. We also described the classes available for constructing RNN cells, models, and layers in TensorFlow and Keras. We built a simple RNN network for classifying the digits of the MNIST dataset.
In next chapter, we shall learn how to build and train the RNN models for time series data.
