Implementing a multilayer RNN for sequence modeling in TensorFlow

Now that we introduced the underlying theory behind RNNs, we are ready to move on to the more practical part to implement RNNs in TensorFlow. During the rest of this chapter, we will apply RNNs to two common problems tasks:

1. Sentiment analysis
2. Language modeling

These two projects, which we'll build together in the following pages, are both fascinating but also quite involved. Thus, instead of providing all the code all at once, we will break the implementation up into several steps and discuss the code in detail. If you like to have a big picture overview and see all the code at once before diving into the discussion, we recommend you to take a look at the code implementation first, which you can view at https://github.com/rasbt/python-machine-learning-book-2nd-edition/blob/master/code/ch16/ch16.ipynb.

Note, before we start coding in this chapter, that since we're using a very modern build of TensorFlow, we'll be...