Shifting gears away from the Space Shuttle, let's work through how to set up, train, and evaluate a deep learning model. You see these used quite a bit for image classification, NLP, and so on. However, let's look at using it for regression. You don't find too many examples of that in my opinion. As such, let's go with our Ames housing price data we used back in Chapter 2, Linear Regression. Before that, let's briefly discuss what Tensor, TensorFlow, and Keras are.
I mentioned earlier that Keras is an API, a frontend if you will, for several deep learning backends. It was originally available only for Python but has been available in R since, mid-2017. It is important to spend some time reviewing its capabilities at its documentation source: https://keras.io/why-use-keras/.
I must confess my colleagues brought me into Keras and using TensorFlow kicking and screaming. If I can get this to work, I would say that you certainly can. I...