In this chapter, we learned about how to build a simple multilayer neural network and an autoencoder. We also explored the design and implementation of a probabilistic graphical model, the RBM, used in an unsupervised manner to create a recommendation engine for films.
It is highly recommended that you try these models and architectures on other pieces of data to see how they perform.
In the next chapter, we will have a look at the hardware side of deep learning, and also find out how exactly CPUs and GPUs serve our computational needs.
