Hands-On Deep Learning with Go

Beyond Basic Neural Networks - Autoencoders and RBMs

Now that we have learned how to build and train a simple neural network, we should build some models that are suitable for real-world problems.

In this chapter, we will discuss how to build a model to recognize and generate handwriting, as well as perform collaborative filtering.

In this chapter, we will cover the following topics:

• Loading data – the Modified National Institute of Standards and Technology (MNIST) database
• Building a neural network for handwriting recognition
• Building an autoencoder – generating MNIST digits
• Building a Restricted Boltzmann Machine (RBM) for Netflix-style collaborative filtering