Summary
We've covered a lot of ground in this chapter! We began with an overview of Neural Networks, focusing on the general properties of topology and learning method before taking a deep dive into the RBM algorithm and RBM code itself. We took this solid understanding forward to create a DBN. In doing so, we linked the DBN theory and code together, before firing up our DBN to work over the MNIST dataset. We performed image classification in a 10-class problem and achieved an extremely competitive result, with classification error below 2%!
In the next chapter, we'll continue to build on your mastery of deep learning by introducing you to another deep learning architecture—Stacked Denoising Autoencoders (SDA).
